charlie880624/STDC
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[Enhancement] Change readme style and Update metafiles. (#895)

Browse Source 
* [Enhancement] Change readme style and prepare for metafiles update.

* Update apcnet github repo url.

* add code snippet.

* split code snippet & official repo.

* update md2yml hook.

* Update metafiles.

* Add converted from attribute.

* process conflict.

* Put defualt variable value.

* update bisenet v2 metafile.

* checkout to ubuntu environment.

* pop empty attribute & make task attribute list.

* update readme style

* update readme style

* update metafiles

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
This commit is contained in:
sennnnn 2021-09-28 16:25:37 +08:00 committed by GitHub
parent 36eb2d8beb
commit 2aa632ebe7
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
72 changed files with 3262 additions and 2573 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

112
.dev/md2yml.py
View File

@ -9,25 +9,28 @@
import glob import glob
import os import os
import os.path as osp import os.path as osp
import re
import sys import sys
import mmcv import mmcv
from lxml import etree
MMSEG_ROOT = osp.dirname(osp.dirname((osp.dirname(__file__)))) MMSEG_ROOT = osp.dirname(osp.dirname((osp.dirname(__file__))))
def dump_yaml_and_check_difference(obj, filename): def dump_yaml_and_check_difference(obj, filename, sort_keys=False):
"""Dump object to a yaml file, and check if the file content is different """Dump object to a yaml file, and check if the file content is different
from the original. from the original.
Args: Args:
obj (any): The python object to be dumped. obj (any): The python object to be dumped.
filename (str): YAML filename to dump the object to. filename (str): YAML filename to dump the object to.
sort_keys (str); Sort key by dictionary order.
Returns: Returns:
Bool: If the target YAML file is different from the original. Bool: If the target YAML file is different from the original.
""" """
str_dump = mmcv.dump(obj, None, file_format='yaml', sort_keys=True) str_dump = mmcv.dump(obj, None, file_format='yaml', sort_keys=sort_keys)
if osp.isfile(filename): if osp.isfile(filename):
file_exists = True file_exists = True
with open(filename, 'r', encoding='utf-8') as f: with open(filename, 'r', encoding='utf-8') as f:
@ -54,12 +57,29 @@ def parse_md(md_file):
Returns: Returns:
Bool: If the target YAML file is different from the original. Bool: If the target YAML file is different from the original.
""" """
collection_name = osp.dirname(md_file).split('/')[-1] collection_name = osp.split(osp.dirname(md_file))[1]
configs = os.listdir(osp.dirname(md_file)) configs = os.listdir(osp.dirname(md_file))
collection = dict(Name=collection_name, Metadata={'Training Data': []}) collection = dict(
Name=collection_name,
Metadata={'Training Data': []},
Paper={
'URL': '',
'Title': ''
},
README=md_file,
Code={
'URL': '',
'Version': ''
})
collection.update({'Converted From': {'Weights': '', 'Code': ''}})
models = [] models = []
datasets = [] datasets = []
paper_url = None
paper_title = None
code_url = None
code_version = None
repo_url = None
with open(md_file, 'r') as md: with open(md_file, 'r') as md:
lines = md.readlines() lines = md.readlines()
@ -70,7 +90,36 @@ def parse_md(md_file):
if len(line) == 0: if len(line) == 0:
i += 1 i += 1
continue continue
if line[:3] == '###': if line[:2] == '# ':
paper_title = line.replace('# ', '')
i += 1
elif line[:3] == '<a ':
content = etree.HTML(line)
node = content.xpath('//a')[0]
if node.text == 'Code Snippet':
code_url = node.get('href', None)
assert code_url is not None, (
f'{collection_name} hasn\'t code snippet url.')
# version extraction
filter_str = r'blob/(.*)/mm'
pattern = re.compile(filter_str)
code_version = pattern.findall(code_url)
assert len(code_version) == 1, (
f'false regular expression ({filter_str}) use.')
code_version = code_version[0]
elif node.text == 'Official Repo':
repo_url = node.get('href', None)
assert repo_url is not None, (
f'{collection_name} hasn\'t official repo url.')
i += 1
elif line[:9] == '<summary ':
content = etree.HTML(line)
nodes = content.xpath('//a')
assert len(nodes) == 1, (
'summary tag should only have single a tag.')
paper_url = nodes[0].get('href', None)
i += 1
elif line[:4] == '### ':
datasets.append(line[4:]) datasets.append(line[4:])
current_dataset = line[4:] current_dataset = line[4:]
i += 2 i += 2
@ -113,22 +162,28 @@ def parse_md(md_file):
crop_size = els[crop_size_id].split('x') crop_size = els[crop_size_id].split('x')
assert len(crop_size) == 2 assert len(crop_size) == 2
model = { model = {
'Name': model_name, 'Name':
'In Collection': collection_name, model_name,
'In Collection':
collection_name,
'Metadata': { 'Metadata': {
'backbone': els[backbone_id], 'backbone': els[backbone_id],
'crop size': f'({crop_size[0]},{crop_size[1]})', 'crop size': f'({crop_size[0]},{crop_size[1]})',
'lr schd': int(els[lr_schd_id]), 'lr schd': int(els[lr_schd_id]),
}, },
'Results': { 'Results': [
'Task': 'Semantic Segmentation', {
'Dataset': current_dataset, 'Task': 'Semantic Segmentation',
'Metrics': { 'Dataset': current_dataset,
'mIoU': float(els[ss_id]), 'Metrics': {
'mIoU': float(els[ss_id]),
},
}, },
}, ],
'Config': config, 'Config':
'Weights': weight, config,
'Weights':
weight,
} }
if fps != -1: if fps != -1:
try: try:
@ -152,15 +207,38 @@ def parse_md(md_file):
}] }]
if mem != -1: if mem != -1:
model['Metadata']['memory (GB)'] = float(mem) model['Metadata']['memory (GB)'] = float(mem)
# Only have semantic segmentation now
if ms_id and els[ms_id] != '-' and els[ms_id] != '': if ms_id and els[ms_id] != '-' and els[ms_id] != '':
model['Results']['Metrics']['mIoU(ms+flip)'] = float( model['Results'][0]['Metrics'][
els[ms_id]) 'mIoU(ms+flip)'] = float(els[ms_id])
models.append(model) models.append(model)
j += 1 j += 1
i = j i = j
else: else:
i += 1 i += 1
flag = (code_url is not None) and (paper_url is not None) and (repo_url
is not None)
assert flag, f'{collection_name} readme error'
collection['Metadata']['Training Data'] = datasets collection['Metadata']['Training Data'] = datasets
collection['Code']['URL'] = code_url
collection['Code']['Version'] = code_version
collection['Paper']['URL'] = paper_url
collection['Paper']['Title'] = paper_title
collection['Converted From']['Code'] = repo_url
# ['Converted From']['Weights] miss
# remove empty attribute
check_key_list = ['Code', 'Paper', 'Converted From']
for check_key in check_key_list:
key_list = list(collection[check_key].keys())
for key in key_list:
if check_key not in collection:
break
if collection[check_key][key] == '':
if len(collection[check_key].keys()) == 1:
collection.pop(check_key)
else:
collection[check_key].pop(key)
result = {'Collections': [collection], 'Models': models} result = {'Collections': [collection], 'Models': models}
yml_file = f'{md_file[:-9]}{collection_name}.yml' yml_file = f'{md_file[:-9]}{collection_name}.yml'
return dump_yaml_and_check_difference(result, yml_file) return dump_yaml_and_check_difference(result, yml_file)

2
.pre-commit-config.yaml
View File

@ -45,7 +45,7 @@ repos:
name: update-model-index name: update-model-index
description: Collect model information and update model-index.yml description: Collect model information and update model-index.yml
entry: .dev/md2yml.py entry: .dev/md2yml.py
additional_dependencies: [mmcv] additional_dependencies: [mmcv, lxml]
language: python language: python
files: ^configs/.*\.md$ files: ^configs/.*\.md$
require_serial: true require_serial: true

3
README.md
View File

@ -66,6 +66,7 @@ Supported backbones:
- [x] [MobileNetV3 (ICCV'2019)](configs/mobilenet_v3) - [x] [MobileNetV3 (ICCV'2019)](configs/mobilenet_v3)
- [x] [Vision Transformer (ICLR'2021)](configs/vit) - [x] [Vision Transformer (ICLR'2021)](configs/vit)
- [x] [Swin Transformer (ArXiv'2021)](configs/swin) - [x] [Swin Transformer (ArXiv'2021)](configs/swin)
- [x] [BiSeNetV2 (IJCV'2021)](configs/bisenetv2)
Supported methods: Supported methods:
@ -94,7 +95,7 @@ Supported methods:
- [x] [PointRend (CVPR'2020)](configs/point_rend) - [x] [PointRend (CVPR'2020)](configs/point_rend)
- [x] [CGNet (TIP'2020)](configs/cgnet) - [x] [CGNet (TIP'2020)](configs/cgnet)
- [x] [SETR (CVPR'2021)](configs/setr) - [x] [SETR (CVPR'2021)](configs/setr)
- [x] [BiSeNetV2 (IJCV'2021)](configs/bisenetv2) - [x] [DPT (ArXiv'2021)](configs/dpt)
- [x] [SegFormer (ArXiv'2021)](configs/segformer) - [x] [SegFormer (ArXiv'2021)](configs/segformer)
Supported datasets: Supported datasets:

3
README_zh-CN.md
View File

@ -65,6 +65,7 @@ MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 O
- [x] [MobileNetV3 (ICCV'2019)](configs/mobilenet_v3) - [x] [MobileNetV3 (ICCV'2019)](configs/mobilenet_v3)
- [x] [Vision Transformer (ICLR'2021)](configs/vit) - [x] [Vision Transformer (ICLR'2021)](configs/vit)
- [x] [Swin Transformer (ArXiv'2021)](configs/swin) - [x] [Swin Transformer (ArXiv'2021)](configs/swin)
- [x] [BiSeNetV2 (IJCV'2021)](configs/bisenetv2)
已支持的算法： 已支持的算法：
@ -93,7 +94,7 @@ MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 O
- [x] [PointRend (CVPR'2020)](configs/point_rend) - [x] [PointRend (CVPR'2020)](configs/point_rend)
- [x] [CGNet (TIP'2020)](configs/cgnet) - [x] [CGNet (TIP'2020)](configs/cgnet)
- [x] [SETR (CVPR'2021)](configs/setr) - [x] [SETR (CVPR'2021)](configs/setr)
- [x] [BiSeNetV2 (IJCV'2021)](configs/bisenetv2) - [x] [DPT (ArXiv'2021)](configs/dpt)
- [x] [SegFormer (ArXiv'2021)](configs/segformer) - [x] [SegFormer (ArXiv'2021)](configs/segformer)
已支持的数据集： 已支持的数据集：

9
configs/ann/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/MendelXu/ANN">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1908.07678">ANN (ICCV'2019)</a></summary>
```latex ```latex
@inproceedings{zhu2019asymmetric, @inproceedings{zhu2019asymmetric,
title={Asymmetric non-local neural networks for semantic segmentation}, title={Asymmetric non-local neural networks for semantic segmentation},
@ -14,6 +21,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

173
configs/ann/ann.yml
View File

@ -1,296 +1,305 @@
Collections: Collections:
- Metadata: - Name: ann
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20K - ADE20K
- Pascal VOC 2012 + Aug - Pascal VOC 2012 + Aug
Name: ann Paper:
URL: https://arxiv.org/abs/1908.07678
Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
README: configs/ann/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ann_head.py#L185
Version: v0.17.0
Converted From:
Code: https://github.com/MendelXu/ANN
Models: Models:
- Config: configs/ann/ann_r50-d8_512x1024_40k_cityscapes.py - Name: ann_r50-d8_512x1024_40k_cityscapes
In Collection: ann In Collection: ann
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 269.54
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 269.54
lr schd: 40000
memory (GB): 6.0 memory (GB): 6.0
Name: ann_r50-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.4 mIoU: 77.4
mIoU(ms+flip): 78.57 mIoU(ms+flip): 78.57
Task: Semantic Segmentation Config: configs/ann/ann_r50-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211-049fc292.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211-049fc292.pth
- Config: configs/ann/ann_r101-d8_512x1024_40k_cityscapes.py - Name: ann_r101-d8_512x1024_40k_cityscapes
In Collection: ann In Collection: ann
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 392.16
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 392.16
lr schd: 40000
memory (GB): 9.5 memory (GB): 9.5
Name: ann_r101-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 76.55 mIoU: 76.55
mIoU(ms+flip): 78.85 mIoU(ms+flip): 78.85
Task: Semantic Segmentation Config: configs/ann/ann_r101-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_40k_cityscapes/ann_r101-d8_512x1024_40k_cityscapes_20200605_095243-adf6eece.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_40k_cityscapes/ann_r101-d8_512x1024_40k_cityscapes_20200605_095243-adf6eece.pth
- Config: configs/ann/ann_r50-d8_769x769_40k_cityscapes.py - Name: ann_r50-d8_769x769_40k_cityscapes
In Collection: ann In Collection: ann
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 588.24
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 588.24
lr schd: 40000
memory (GB): 6.8 memory (GB): 6.8
Name: ann_r50-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.89 mIoU: 78.89
mIoU(ms+flip): 80.46 mIoU(ms+flip): 80.46
Task: Semantic Segmentation Config: configs/ann/ann_r50-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_40k_cityscapes/ann_r50-d8_769x769_40k_cityscapes_20200530_025712-2b46b04d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_40k_cityscapes/ann_r50-d8_769x769_40k_cityscapes_20200530_025712-2b46b04d.pth
- Config: configs/ann/ann_r101-d8_769x769_40k_cityscapes.py - Name: ann_r101-d8_769x769_40k_cityscapes
In Collection: ann In Collection: ann
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 869.57
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 869.57
lr schd: 40000
memory (GB): 10.7 memory (GB): 10.7
Name: ann_r101-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.32 mIoU: 79.32
mIoU(ms+flip): 80.94 mIoU(ms+flip): 80.94
Task: Semantic Segmentation Config: configs/ann/ann_r101-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_40k_cityscapes/ann_r101-d8_769x769_40k_cityscapes_20200530_025720-059bff28.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_40k_cityscapes/ann_r101-d8_769x769_40k_cityscapes_20200530_025720-059bff28.pth
- Config: configs/ann/ann_r50-d8_512x1024_80k_cityscapes.py - Name: ann_r50-d8_512x1024_80k_cityscapes
In Collection: ann In Collection: ann
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: ann_r50-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.34 mIoU: 77.34
mIoU(ms+flip): 78.65 mIoU(ms+flip): 78.65
Task: Semantic Segmentation Config: configs/ann/ann_r50-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_80k_cityscapes/ann_r50-d8_512x1024_80k_cityscapes_20200607_101911-5a9ad545.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_80k_cityscapes/ann_r50-d8_512x1024_80k_cityscapes_20200607_101911-5a9ad545.pth
- Config: configs/ann/ann_r101-d8_512x1024_80k_cityscapes.py - Name: ann_r101-d8_512x1024_80k_cityscapes
In Collection: ann In Collection: ann
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: ann_r101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.14 mIoU: 77.14
mIoU(ms+flip): 78.81 mIoU(ms+flip): 78.81
Task: Semantic Segmentation Config: configs/ann/ann_r101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_80k_cityscapes/ann_r101-d8_512x1024_80k_cityscapes_20200607_013728-aceccc6e.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_80k_cityscapes/ann_r101-d8_512x1024_80k_cityscapes_20200607_013728-aceccc6e.pth
- Config: configs/ann/ann_r50-d8_769x769_80k_cityscapes.py - Name: ann_r50-d8_769x769_80k_cityscapes
In Collection: ann In Collection: ann
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: ann_r50-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.88 mIoU: 78.88
mIoU(ms+flip): 80.57 mIoU(ms+flip): 80.57
Task: Semantic Segmentation Config: configs/ann/ann_r50-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_80k_cityscapes/ann_r50-d8_769x769_80k_cityscapes_20200607_044426-cc7ff323.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_80k_cityscapes/ann_r50-d8_769x769_80k_cityscapes_20200607_044426-cc7ff323.pth
- Config: configs/ann/ann_r101-d8_769x769_80k_cityscapes.py - Name: ann_r101-d8_769x769_80k_cityscapes
In Collection: ann In Collection: ann
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: ann_r101-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.8 mIoU: 78.8
mIoU(ms+flip): 80.34 mIoU(ms+flip): 80.34
Task: Semantic Segmentation Config: configs/ann/ann_r101-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_80k_cityscapes/ann_r101-d8_769x769_80k_cityscapes_20200607_013713-a9d4be8d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_80k_cityscapes/ann_r101-d8_769x769_80k_cityscapes_20200607_013713-a9d4be8d.pth
- Config: configs/ann/ann_r50-d8_512x512_80k_ade20k.py - Name: ann_r50-d8_512x512_80k_ade20k
In Collection: ann In Collection: ann
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 47.6
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 47.6
lr schd: 80000
memory (GB): 9.1 memory (GB): 9.1
Name: ann_r50-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 41.01 mIoU: 41.01
mIoU(ms+flip): 42.3 mIoU(ms+flip): 42.3
Task: Semantic Segmentation Config: configs/ann/ann_r50-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_80k_ade20k/ann_r50-d8_512x512_80k_ade20k_20200615_014818-26f75e11.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_80k_ade20k/ann_r50-d8_512x512_80k_ade20k_20200615_014818-26f75e11.pth
- Config: configs/ann/ann_r101-d8_512x512_80k_ade20k.py - Name: ann_r101-d8_512x512_80k_ade20k
In Collection: ann In Collection: ann
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 70.82
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 70.82
lr schd: 80000
memory (GB): 12.5 memory (GB): 12.5
Name: ann_r101-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.94 mIoU: 42.94
mIoU(ms+flip): 44.18 mIoU(ms+flip): 44.18
Task: Semantic Segmentation Config: configs/ann/ann_r101-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_80k_ade20k/ann_r101-d8_512x512_80k_ade20k_20200615_014818-c0153543.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_80k_ade20k/ann_r101-d8_512x512_80k_ade20k_20200615_014818-c0153543.pth
- Config: configs/ann/ann_r50-d8_512x512_160k_ade20k.py - Name: ann_r50-d8_512x512_160k_ade20k
In Collection: ann In Collection: ann
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: ann_r50-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 41.74 mIoU: 41.74
mIoU(ms+flip): 42.62 mIoU(ms+flip): 42.62
Task: Semantic Segmentation Config: configs/ann/ann_r50-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_160k_ade20k/ann_r50-d8_512x512_160k_ade20k_20200615_231733-892247bc.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_160k_ade20k/ann_r50-d8_512x512_160k_ade20k_20200615_231733-892247bc.pth
- Config: configs/ann/ann_r101-d8_512x512_160k_ade20k.py - Name: ann_r101-d8_512x512_160k_ade20k
In Collection: ann In Collection: ann
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: ann_r101-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.94 mIoU: 42.94
mIoU(ms+flip): 44.06 mIoU(ms+flip): 44.06
Task: Semantic Segmentation Config: configs/ann/ann_r101-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_160k_ade20k/ann_r101-d8_512x512_160k_ade20k_20200615_231733-955eb1ec.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_160k_ade20k/ann_r101-d8_512x512_160k_ade20k_20200615_231733-955eb1ec.pth
- Config: configs/ann/ann_r50-d8_512x512_20k_voc12aug.py - Name: ann_r50-d8_512x512_20k_voc12aug
In Collection: ann In Collection: ann
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 47.8
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 47.8
lr schd: 20000
memory (GB): 6.0 memory (GB): 6.0
Name: ann_r50-d8_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 74.86 mIoU: 74.86
mIoU(ms+flip): 76.13 mIoU(ms+flip): 76.13
Task: Semantic Segmentation Config: configs/ann/ann_r50-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_20k_voc12aug/ann_r50-d8_512x512_20k_voc12aug_20200617_222246-dfcb1c62.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_20k_voc12aug/ann_r50-d8_512x512_20k_voc12aug_20200617_222246-dfcb1c62.pth
- Config: configs/ann/ann_r101-d8_512x512_20k_voc12aug.py - Name: ann_r101-d8_512x512_20k_voc12aug
In Collection: ann In Collection: ann
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 71.74
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 71.74
lr schd: 20000
memory (GB): 9.5 memory (GB): 9.5
Name: ann_r101-d8_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 77.47 mIoU: 77.47
mIoU(ms+flip): 78.7 mIoU(ms+flip): 78.7
Task: Semantic Segmentation Config: configs/ann/ann_r101-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_20k_voc12aug/ann_r101-d8_512x512_20k_voc12aug_20200617_222246-2fad0042.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_20k_voc12aug/ann_r101-d8_512x512_20k_voc12aug_20200617_222246-2fad0042.pth
- Config: configs/ann/ann_r50-d8_512x512_40k_voc12aug.py - Name: ann_r50-d8_512x512_40k_voc12aug
In Collection: ann In Collection: ann
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: ann_r50-d8_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 76.56 mIoU: 76.56
mIoU(ms+flip): 77.51 mIoU(ms+flip): 77.51
Task: Semantic Segmentation Config: configs/ann/ann_r50-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_40k_voc12aug/ann_r50-d8_512x512_40k_voc12aug_20200613_231314-b5dac322.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_40k_voc12aug/ann_r50-d8_512x512_40k_voc12aug_20200613_231314-b5dac322.pth
- Config: configs/ann/ann_r101-d8_512x512_40k_voc12aug.py - Name: ann_r101-d8_512x512_40k_voc12aug
In Collection: ann In Collection: ann
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: ann_r101-d8_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 76.7 mIoU: 76.7
mIoU(ms+flip): 78.06 mIoU(ms+flip): 78.06
Task: Semantic Segmentation Config: configs/ann/ann_r101-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_40k_voc12aug/ann_r101-d8_512x512_40k_voc12aug_20200613_231314-bd205bbe.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_40k_voc12aug/ann_r101-d8_512x512_40k_voc12aug_20200613_231314-bd205bbe.pth

9
configs/apcnet/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/Junjun2016/APCNet">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111">Code Snippet</a>
<details>
<summary align="right"><a href="https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html">APCNet (CVPR'2019)</a></summary>
```latex ```latex
@InProceedings{He_2019_CVPR, @InProceedings{He_2019_CVPR,
author = {He, Junjun and Deng, Zhongying and Zhou, Lei and Wang, Yali and Qiao, Yu}, author = {He, Junjun and Deng, Zhongying and Zhou, Lei and Wang, Yali and Qiao, Yu},
@ -14,6 +21,8 @@ year = {2019}
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

133
configs/apcnet/apcnet.yml
View File

@ -1,223 +1,232 @@
Collections: Collections:
- Metadata: - Name: apcnet
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20K - ADE20K
Name: apcnet Paper:
URL: https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html
Title: Adaptive Pyramid Context Network for Semantic Segmentation
README: configs/apcnet/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
Version: v0.17.0
Converted From:
Code: https://github.com/Junjun2016/APCNet
Models: Models:
- Config: configs/apcnet/apcnet_r50-d8_512x1024_40k_cityscapes.py - Name: apcnet_r50-d8_512x1024_40k_cityscapes
In Collection: apcnet In Collection: apcnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 280.11
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 280.11
lr schd: 40000
memory (GB): 7.7 memory (GB): 7.7
Name: apcnet_r50-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.02 mIoU: 78.02
mIoU(ms+flip): 79.26 mIoU(ms+flip): 79.26
Task: Semantic Segmentation Config: configs/apcnet/apcnet_r50-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_40k_cityscapes/apcnet_r50-d8_512x1024_40k_cityscapes_20201214_115717-5e88fa33.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_40k_cityscapes/apcnet_r50-d8_512x1024_40k_cityscapes_20201214_115717-5e88fa33.pth
- Config: configs/apcnet/apcnet_r101-d8_512x1024_40k_cityscapes.py - Name: apcnet_r101-d8_512x1024_40k_cityscapes
In Collection: apcnet In Collection: apcnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 465.12
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 465.12
lr schd: 40000
memory (GB): 11.2 memory (GB): 11.2
Name: apcnet_r101-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.08 mIoU: 79.08
mIoU(ms+flip): 80.34 mIoU(ms+flip): 80.34
Task: Semantic Segmentation Config: configs/apcnet/apcnet_r101-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_40k_cityscapes/apcnet_r101-d8_512x1024_40k_cityscapes_20201214_115716-abc9d111.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_40k_cityscapes/apcnet_r101-d8_512x1024_40k_cityscapes_20201214_115716-abc9d111.pth
- Config: configs/apcnet/apcnet_r50-d8_769x769_40k_cityscapes.py - Name: apcnet_r50-d8_769x769_40k_cityscapes
In Collection: apcnet In Collection: apcnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 657.89
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 657.89
lr schd: 40000
memory (GB): 8.7 memory (GB): 8.7
Name: apcnet_r50-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.89 mIoU: 77.89
mIoU(ms+flip): 79.75 mIoU(ms+flip): 79.75
Task: Semantic Segmentation Config: configs/apcnet/apcnet_r50-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_40k_cityscapes/apcnet_r50-d8_769x769_40k_cityscapes_20201214_115717-2a2628d7.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_40k_cityscapes/apcnet_r50-d8_769x769_40k_cityscapes_20201214_115717-2a2628d7.pth
- Config: configs/apcnet/apcnet_r101-d8_769x769_40k_cityscapes.py - Name: apcnet_r101-d8_769x769_40k_cityscapes
In Collection: apcnet In Collection: apcnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 970.87
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 970.87
lr schd: 40000
memory (GB): 12.7 memory (GB): 12.7
Name: apcnet_r101-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.96 mIoU: 77.96
mIoU(ms+flip): 79.24 mIoU(ms+flip): 79.24
Task: Semantic Segmentation Config: configs/apcnet/apcnet_r101-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_40k_cityscapes/apcnet_r101-d8_769x769_40k_cityscapes_20201214_115718-b650de90.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_40k_cityscapes/apcnet_r101-d8_769x769_40k_cityscapes_20201214_115718-b650de90.pth
- Config: configs/apcnet/apcnet_r50-d8_512x1024_80k_cityscapes.py - Name: apcnet_r50-d8_512x1024_80k_cityscapes
In Collection: apcnet In Collection: apcnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: apcnet_r50-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.96 mIoU: 78.96
mIoU(ms+flip): 79.94 mIoU(ms+flip): 79.94
Task: Semantic Segmentation Config: configs/apcnet/apcnet_r50-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_80k_cityscapes/apcnet_r50-d8_512x1024_80k_cityscapes_20201214_115716-987f51e3.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_80k_cityscapes/apcnet_r50-d8_512x1024_80k_cityscapes_20201214_115716-987f51e3.pth
- Config: configs/apcnet/apcnet_r101-d8_512x1024_80k_cityscapes.py - Name: apcnet_r101-d8_512x1024_80k_cityscapes
In Collection: apcnet In Collection: apcnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: apcnet_r101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.64 mIoU: 79.64
mIoU(ms+flip): 80.61 mIoU(ms+flip): 80.61
Task: Semantic Segmentation Config: configs/apcnet/apcnet_r101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_80k_cityscapes/apcnet_r101-d8_512x1024_80k_cityscapes_20201214_115705-b1ff208a.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_80k_cityscapes/apcnet_r101-d8_512x1024_80k_cityscapes_20201214_115705-b1ff208a.pth
- Config: configs/apcnet/apcnet_r50-d8_769x769_80k_cityscapes.py - Name: apcnet_r50-d8_769x769_80k_cityscapes
In Collection: apcnet In Collection: apcnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: apcnet_r50-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.79 mIoU: 78.79
mIoU(ms+flip): 80.35 mIoU(ms+flip): 80.35
Task: Semantic Segmentation Config: configs/apcnet/apcnet_r50-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_80k_cityscapes/apcnet_r50-d8_769x769_80k_cityscapes_20201214_115718-7ea9fa12.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_80k_cityscapes/apcnet_r50-d8_769x769_80k_cityscapes_20201214_115718-7ea9fa12.pth
- Config: configs/apcnet/apcnet_r101-d8_769x769_80k_cityscapes.py - Name: apcnet_r101-d8_769x769_80k_cityscapes
In Collection: apcnet In Collection: apcnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: apcnet_r101-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.45 mIoU: 78.45
mIoU(ms+flip): 79.91 mIoU(ms+flip): 79.91
Task: Semantic Segmentation Config: configs/apcnet/apcnet_r101-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_80k_cityscapes/apcnet_r101-d8_769x769_80k_cityscapes_20201214_115716-a7fbc2ab.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_80k_cityscapes/apcnet_r101-d8_769x769_80k_cityscapes_20201214_115716-a7fbc2ab.pth
- Config: configs/apcnet/apcnet_r50-d8_512x512_80k_ade20k.py - Name: apcnet_r50-d8_512x512_80k_ade20k
In Collection: apcnet In Collection: apcnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 50.99
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 50.99
lr schd: 80000
memory (GB): 10.1 memory (GB): 10.1
Name: apcnet_r50-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.2 mIoU: 42.2
mIoU(ms+flip): 43.3 mIoU(ms+flip): 43.3
Task: Semantic Segmentation Config: configs/apcnet/apcnet_r50-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_80k_ade20k/apcnet_r50-d8_512x512_80k_ade20k_20201214_115705-a8626293.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_80k_ade20k/apcnet_r50-d8_512x512_80k_ade20k_20201214_115705-a8626293.pth
- Config: configs/apcnet/apcnet_r101-d8_512x512_80k_ade20k.py - Name: apcnet_r101-d8_512x512_80k_ade20k
In Collection: apcnet In Collection: apcnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 76.34
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 76.34
lr schd: 80000
memory (GB): 13.6 memory (GB): 13.6
Name: apcnet_r101-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 45.54 mIoU: 45.54
mIoU(ms+flip): 46.65 mIoU(ms+flip): 46.65
Task: Semantic Segmentation Config: configs/apcnet/apcnet_r101-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_80k_ade20k/apcnet_r101-d8_512x512_80k_ade20k_20201214_115704-c656c3fb.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_80k_ade20k/apcnet_r101-d8_512x512_80k_ade20k_20201214_115704-c656c3fb.pth
- Config: configs/apcnet/apcnet_r50-d8_512x512_160k_ade20k.py - Name: apcnet_r50-d8_512x512_160k_ade20k
In Collection: apcnet In Collection: apcnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: apcnet_r50-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 43.4 mIoU: 43.4
mIoU(ms+flip): 43.94 mIoU(ms+flip): 43.94
Task: Semantic Segmentation Config: configs/apcnet/apcnet_r50-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_160k_ade20k/apcnet_r50-d8_512x512_160k_ade20k_20201214_115706-25fb92c2.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_160k_ade20k/apcnet_r50-d8_512x512_160k_ade20k_20201214_115706-25fb92c2.pth
- Config: configs/apcnet/apcnet_r101-d8_512x512_160k_ade20k.py - Name: apcnet_r101-d8_512x512_160k_ade20k
In Collection: apcnet In Collection: apcnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: apcnet_r101-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 45.41 mIoU: 45.41
mIoU(ms+flip): 46.63 mIoU(ms+flip): 46.63
Task: Semantic Segmentation Config: configs/apcnet/apcnet_r101-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_160k_ade20k/apcnet_r101-d8_512x512_160k_ade20k_20201214_115705-73f9a8d7.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_160k_ade20k/apcnet_r101-d8_512x512_160k_ade20k_20201214_115705-73f9a8d7.pth

9
configs/bisenetv2/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv2.py#L545">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/2004.02147">BiSeNetV2 (IJCV'2021)</a></summary>
```latex ```latex
@article{yu2021bisenet, @article{yu2021bisenet,
title={Bisenet v2: Bilateral network with guided aggregation for real-time semantic segmentation}, title={Bisenet v2: Bilateral network with guided aggregation for real-time semantic segmentation},
@ -15,6 +22,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

52
configs/bisenetv2/bisenetv2.yml
View File

@ -1,80 +1,88 @@
Collections: Collections:
- Metadata: - Name: bisenetv2
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
Name: bisenetv2 Paper:
URL: https://arxiv.org/abs/2004.02147
Title: 'Bisenet v2: Bilateral Network with Guided Aggregation for Real-time Semantic
Segmentation'
README: configs/bisenetv2/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv2.py#L545
Version: v0.18.0
Models: Models:
- Config: configs/bisenetv2/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes.py - Name: bisenetv2_fcn_4x4_1024x1024_160k_cityscapes
In Collection: bisenetv2 In Collection: bisenetv2
Metadata: Metadata:
backbone: BiSeNetV2 backbone: BiSeNetV2
crop size: (1024,1024) crop size: (1024,1024)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 31.48
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (1024,1024) resolution: (1024,1024)
value: 31.48
lr schd: 160000
memory (GB): 7.64 memory (GB): 7.64
Name: bisenetv2_fcn_4x4_1024x1024_160k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 73.21 mIoU: 73.21
mIoU(ms+flip): 75.74 mIoU(ms+flip): 75.74
Task: Semantic Segmentation Config: configs/bisenetv2/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes_20210902_015551-bcf10f09.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_4x4_1024x1024_160k_cityscapes_20210902_015551-bcf10f09.pth
- Config: configs/bisenetv2/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes.py - Name: bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes
In Collection: bisenetv2 In Collection: bisenetv2
Metadata: Metadata:
backbone: BiSeNetV2 backbone: BiSeNetV2
crop size: (1024,1024) crop size: (1024,1024)
lr schd: 160000 lr schd: 160000
memory (GB): 7.64 memory (GB): 7.64
Name: bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 73.57 mIoU: 73.57
mIoU(ms+flip): 75.8 mIoU(ms+flip): 75.8
Task: Semantic Segmentation Config: configs/bisenetv2/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes_20210902_112947-5f8103b4.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_ohem_4x4_1024x1024_160k_cityscapes_20210902_112947-5f8103b4.pth
- Config: configs/bisenetv2/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes.py - Name: bisenetv2_fcn_4x8_1024x1024_160k_cityscapes
In Collection: bisenetv2 In Collection: bisenetv2
Metadata: Metadata:
backbone: BiSeNetV2 backbone: BiSeNetV2
crop size: (1024,1024) crop size: (1024,1024)
lr schd: 160000 lr schd: 160000
memory (GB): 15.05 memory (GB): 15.05
Name: bisenetv2_fcn_4x8_1024x1024_160k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 75.76 mIoU: 75.76
mIoU(ms+flip): 77.79 mIoU(ms+flip): 77.79
Task: Semantic Segmentation Config: configs/bisenetv2/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes_20210903_000032-e1a2eed6.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes/bisenetv2_fcn_4x8_1024x1024_160k_cityscapes_20210903_000032-e1a2eed6.pth
- Config: configs/bisenetv2/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes.py - Name: bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes
In Collection: bisenetv2 In Collection: bisenetv2
Metadata: Metadata:
backbone: BiSeNetV2 backbone: BiSeNetV2
crop size: (1024,1024) crop size: (1024,1024)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 27.29
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (1024,1024) resolution: (1024,1024)
value: 27.29
lr schd: 160000
memory (GB): 5.77 memory (GB): 5.77
Name: bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 73.07 mIoU: 73.07
mIoU(ms+flip): 75.13 mIoU(ms+flip): 75.13
Task: Semantic Segmentation Config: configs/bisenetv2/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes_20210902_045942-b979777b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv2/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes/bisenetv2_fcn_fp16_4x4_1024x1024_160k_cityscapes_20210902_045942-b979777b.pth

9
configs/ccnet/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/speedinghzl/CCNet">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1811.11721">CCNet (ICCV'2019)</a></summary>
```latex ```latex
@article{huang2018ccnet, @article{huang2018ccnet,
title={CCNet: Criss-Cross Attention for Semantic Segmentation}, title={CCNet: Criss-Cross Attention for Semantic Segmentation},
@ -13,6 +20,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

173
configs/ccnet/ccnet.yml
View File

@ -1,296 +1,305 @@
Collections: Collections:
- Metadata: - Name: ccnet
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20K - ADE20K
- Pascal VOC 2012 + Aug - Pascal VOC 2012 + Aug
Name: ccnet Paper:
URL: https://arxiv.org/abs/1811.11721
Title: 'CCNet: Criss-Cross Attention for Semantic Segmentation'
README: configs/ccnet/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/apc_head.py#L111
Version: v0.17.0
Converted From:
Code: https://github.com/speedinghzl/CCNet
Models: Models:
- Config: configs/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes.py - Name: ccnet_r50-d8_512x1024_40k_cityscapes
In Collection: ccnet In Collection: ccnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 301.2
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 301.2
lr schd: 40000
memory (GB): 6.0 memory (GB): 6.0
Name: ccnet_r50-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.76 mIoU: 77.76
mIoU(ms+flip): 78.87 mIoU(ms+flip): 78.87
Task: Semantic Segmentation Config: configs/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes/ccnet_r50-d8_512x1024_40k_cityscapes_20200616_142517-4123f401.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes/ccnet_r50-d8_512x1024_40k_cityscapes_20200616_142517-4123f401.pth
- Config: configs/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes.py - Name: ccnet_r101-d8_512x1024_40k_cityscapes
In Collection: ccnet In Collection: ccnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 432.9
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 432.9
lr schd: 40000
memory (GB): 9.5 memory (GB): 9.5
Name: ccnet_r101-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 76.35 mIoU: 76.35
mIoU(ms+flip): 78.19 mIoU(ms+flip): 78.19
Task: Semantic Segmentation Config: configs/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes/ccnet_r101-d8_512x1024_40k_cityscapes_20200616_142540-a3b84ba6.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes/ccnet_r101-d8_512x1024_40k_cityscapes_20200616_142540-a3b84ba6.pth
- Config: configs/ccnet/ccnet_r50-d8_769x769_40k_cityscapes.py - Name: ccnet_r50-d8_769x769_40k_cityscapes
In Collection: ccnet In Collection: ccnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 699.3
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 699.3
lr schd: 40000
memory (GB): 6.8 memory (GB): 6.8
Name: ccnet_r50-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.46 mIoU: 78.46
mIoU(ms+flip): 79.93 mIoU(ms+flip): 79.93
Task: Semantic Segmentation Config: configs/ccnet/ccnet_r50-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_40k_cityscapes/ccnet_r50-d8_769x769_40k_cityscapes_20200616_145125-76d11884.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_40k_cityscapes/ccnet_r50-d8_769x769_40k_cityscapes_20200616_145125-76d11884.pth
- Config: configs/ccnet/ccnet_r101-d8_769x769_40k_cityscapes.py - Name: ccnet_r101-d8_769x769_40k_cityscapes
In Collection: ccnet In Collection: ccnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 990.1
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 990.1
lr schd: 40000
memory (GB): 10.7 memory (GB): 10.7
Name: ccnet_r101-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 76.94 mIoU: 76.94
mIoU(ms+flip): 78.62 mIoU(ms+flip): 78.62
Task: Semantic Segmentation Config: configs/ccnet/ccnet_r101-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_40k_cityscapes/ccnet_r101-d8_769x769_40k_cityscapes_20200617_101428-4f57c8d0.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_40k_cityscapes/ccnet_r101-d8_769x769_40k_cityscapes_20200617_101428-4f57c8d0.pth
- Config: configs/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes.py - Name: ccnet_r50-d8_512x1024_80k_cityscapes
In Collection: ccnet In Collection: ccnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: ccnet_r50-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.03 mIoU: 79.03
mIoU(ms+flip): 80.16 mIoU(ms+flip): 80.16
Task: Semantic Segmentation Config: configs/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes/ccnet_r50-d8_512x1024_80k_cityscapes_20200617_010421-869a3423.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes/ccnet_r50-d8_512x1024_80k_cityscapes_20200617_010421-869a3423.pth
- Config: configs/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes.py - Name: ccnet_r101-d8_512x1024_80k_cityscapes
In Collection: ccnet In Collection: ccnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: ccnet_r101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.87 mIoU: 78.87
mIoU(ms+flip): 79.9 mIoU(ms+flip): 79.9
Task: Semantic Segmentation Config: configs/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes/ccnet_r101-d8_512x1024_80k_cityscapes_20200617_203935-ffae8917.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes/ccnet_r101-d8_512x1024_80k_cityscapes_20200617_203935-ffae8917.pth
- Config: configs/ccnet/ccnet_r50-d8_769x769_80k_cityscapes.py - Name: ccnet_r50-d8_769x769_80k_cityscapes
In Collection: ccnet In Collection: ccnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: ccnet_r50-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.29 mIoU: 79.29
mIoU(ms+flip): 81.08 mIoU(ms+flip): 81.08
Task: Semantic Segmentation Config: configs/ccnet/ccnet_r50-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_80k_cityscapes/ccnet_r50-d8_769x769_80k_cityscapes_20200617_010421-73eed8ca.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_80k_cityscapes/ccnet_r50-d8_769x769_80k_cityscapes_20200617_010421-73eed8ca.pth
- Config: configs/ccnet/ccnet_r101-d8_769x769_80k_cityscapes.py - Name: ccnet_r101-d8_769x769_80k_cityscapes
In Collection: ccnet In Collection: ccnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: ccnet_r101-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.45 mIoU: 79.45
mIoU(ms+flip): 80.66 mIoU(ms+flip): 80.66
Task: Semantic Segmentation Config: configs/ccnet/ccnet_r101-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_80k_cityscapes/ccnet_r101-d8_769x769_80k_cityscapes_20200618_011502-ad3cd481.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_80k_cityscapes/ccnet_r101-d8_769x769_80k_cityscapes_20200618_011502-ad3cd481.pth
- Config: configs/ccnet/ccnet_r50-d8_512x512_80k_ade20k.py - Name: ccnet_r50-d8_512x512_80k_ade20k
In Collection: ccnet In Collection: ccnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 47.87
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 47.87
lr schd: 80000
memory (GB): 8.8 memory (GB): 8.8
Name: ccnet_r50-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 41.78 mIoU: 41.78
mIoU(ms+flip): 42.98 mIoU(ms+flip): 42.98
Task: Semantic Segmentation Config: configs/ccnet/ccnet_r50-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_80k_ade20k/ccnet_r50-d8_512x512_80k_ade20k_20200615_014848-aa37f61e.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_80k_ade20k/ccnet_r50-d8_512x512_80k_ade20k_20200615_014848-aa37f61e.pth
- Config: configs/ccnet/ccnet_r101-d8_512x512_80k_ade20k.py - Name: ccnet_r101-d8_512x512_80k_ade20k
In Collection: ccnet In Collection: ccnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 70.87
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 70.87
lr schd: 80000
memory (GB): 12.2 memory (GB): 12.2
Name: ccnet_r101-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 43.97 mIoU: 43.97
mIoU(ms+flip): 45.13 mIoU(ms+flip): 45.13
Task: Semantic Segmentation Config: configs/ccnet/ccnet_r101-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_80k_ade20k/ccnet_r101-d8_512x512_80k_ade20k_20200615_014848-1f4929a3.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_80k_ade20k/ccnet_r101-d8_512x512_80k_ade20k_20200615_014848-1f4929a3.pth
- Config: configs/ccnet/ccnet_r50-d8_512x512_160k_ade20k.py - Name: ccnet_r50-d8_512x512_160k_ade20k
In Collection: ccnet In Collection: ccnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: ccnet_r50-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.08 mIoU: 42.08
mIoU(ms+flip): 43.13 mIoU(ms+flip): 43.13
Task: Semantic Segmentation Config: configs/ccnet/ccnet_r50-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_160k_ade20k/ccnet_r50-d8_512x512_160k_ade20k_20200616_084435-7c97193b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_160k_ade20k/ccnet_r50-d8_512x512_160k_ade20k_20200616_084435-7c97193b.pth
- Config: configs/ccnet/ccnet_r101-d8_512x512_160k_ade20k.py - Name: ccnet_r101-d8_512x512_160k_ade20k
In Collection: ccnet In Collection: ccnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: ccnet_r101-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 43.71 mIoU: 43.71
mIoU(ms+flip): 45.04 mIoU(ms+flip): 45.04
Task: Semantic Segmentation Config: configs/ccnet/ccnet_r101-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_160k_ade20k/ccnet_r101-d8_512x512_160k_ade20k_20200616_000644-e849e007.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_160k_ade20k/ccnet_r101-d8_512x512_160k_ade20k_20200616_000644-e849e007.pth
- Config: configs/ccnet/ccnet_r50-d8_512x512_20k_voc12aug.py - Name: ccnet_r50-d8_512x512_20k_voc12aug
In Collection: ccnet In Collection: ccnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 48.9
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 48.9
lr schd: 20000
memory (GB): 6.0 memory (GB): 6.0
Name: ccnet_r50-d8_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 76.17 mIoU: 76.17
mIoU(ms+flip): 77.51 mIoU(ms+flip): 77.51
Task: Semantic Segmentation Config: configs/ccnet/ccnet_r50-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_20k_voc12aug/ccnet_r50-d8_512x512_20k_voc12aug_20200617_193212-fad81784.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_20k_voc12aug/ccnet_r50-d8_512x512_20k_voc12aug_20200617_193212-fad81784.pth
- Config: configs/ccnet/ccnet_r101-d8_512x512_20k_voc12aug.py - Name: ccnet_r101-d8_512x512_20k_voc12aug
In Collection: ccnet In Collection: ccnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 73.31
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 73.31
lr schd: 20000
memory (GB): 9.5 memory (GB): 9.5
Name: ccnet_r101-d8_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 77.27 mIoU: 77.27
mIoU(ms+flip): 79.02 mIoU(ms+flip): 79.02
Task: Semantic Segmentation Config: configs/ccnet/ccnet_r101-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_20k_voc12aug/ccnet_r101-d8_512x512_20k_voc12aug_20200617_193212-0007b61d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_20k_voc12aug/ccnet_r101-d8_512x512_20k_voc12aug_20200617_193212-0007b61d.pth
- Config: configs/ccnet/ccnet_r50-d8_512x512_40k_voc12aug.py - Name: ccnet_r50-d8_512x512_40k_voc12aug
In Collection: ccnet In Collection: ccnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: ccnet_r50-d8_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 75.96 mIoU: 75.96
mIoU(ms+flip): 77.04 mIoU(ms+flip): 77.04
Task: Semantic Segmentation Config: configs/ccnet/ccnet_r50-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_40k_voc12aug/ccnet_r50-d8_512x512_40k_voc12aug_20200613_232127-c2a15f02.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_40k_voc12aug/ccnet_r50-d8_512x512_40k_voc12aug_20200613_232127-c2a15f02.pth
- Config: configs/ccnet/ccnet_r101-d8_512x512_40k_voc12aug.py - Name: ccnet_r101-d8_512x512_40k_voc12aug
In Collection: ccnet In Collection: ccnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: ccnet_r101-d8_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 77.87 mIoU: 77.87
mIoU(ms+flip): 78.9 mIoU(ms+flip): 78.9
Task: Semantic Segmentation Config: configs/ccnet/ccnet_r101-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_40k_voc12aug/ccnet_r101-d8_512x512_40k_voc12aug_20200613_232127-c30da577.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_40k_voc12aug/ccnet_r101-d8_512x512_40k_voc12aug_20200613_232127-c30da577.pth

9
configs/cgnet/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/wutianyiRosun/CGNet">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/cgnet.py#L187">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/pdf/1811.08201.pdf">CGNet (TIP'2020)</a></summary>
```latext ```latext
@article{wu2020cgnet, @article{wu2020cgnet,
title={Cgnet: A light-weight context guided network for semantic segmentation}, title={Cgnet: A light-weight context guided network for semantic segmentation},
@ -16,6 +23,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

41
configs/cgnet/cgnet.yml
View File

@ -1,50 +1,59 @@
Collections: Collections:
- Metadata: - Name: cgnet
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
Name: cgnet Paper:
URL: https://arxiv.org/pdf/1811.08201.pdf
Title: 'CGNet: A Light-weight Context Guided Network for Semantic Segmentation'
README: configs/cgnet/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/cgnet.py#L187
Version: v0.17.0
Converted From:
Code: https://github.com/wutianyiRosun/CGNet
Models: Models:
- Config: configs/cgnet/cgnet_680x680_60k_cityscapes.py - Name: cgnet_680x680_60k_cityscapes
In Collection: cgnet In Collection: cgnet
Metadata: Metadata:
backbone: M3N21 backbone: M3N21
crop size: (680,680) crop size: (680,680)
lr schd: 60000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 32.78
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (680,680) resolution: (680,680)
value: 32.78
lr schd: 60000
memory (GB): 7.5 memory (GB): 7.5
Name: cgnet_680x680_60k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 65.63 mIoU: 65.63
mIoU(ms+flip): 68.04 mIoU(ms+flip): 68.04
Task: Semantic Segmentation Config: configs/cgnet/cgnet_680x680_60k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_680x680_60k_cityscapes/cgnet_680x680_60k_cityscapes_20201101_110253-4c0b2f2d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_680x680_60k_cityscapes/cgnet_680x680_60k_cityscapes_20201101_110253-4c0b2f2d.pth
- Config: configs/cgnet/cgnet_512x1024_60k_cityscapes.py - Name: cgnet_512x1024_60k_cityscapes
In Collection: cgnet In Collection: cgnet
Metadata: Metadata:
backbone: M3N21 backbone: M3N21
crop size: (512,1024) crop size: (512,1024)
lr schd: 60000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 32.11
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 32.11
lr schd: 60000
memory (GB): 8.3 memory (GB): 8.3
Name: cgnet_512x1024_60k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 68.27 mIoU: 68.27
mIoU(ms+flip): 70.33 mIoU(ms+flip): 70.33
Task: Semantic Segmentation Config: configs/cgnet/cgnet_512x1024_60k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_512x1024_60k_cityscapes/cgnet_512x1024_60k_cityscapes_20201101_110254-124ea03b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_512x1024_60k_cityscapes/cgnet_512x1024_60k_cityscapes_20201101_110254-124ea03b.pth

9
configs/danet/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/junfu1115/DANet/">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1809.02983">DANet (CVPR'2019)</a></summary>
```latex ```latex
@article{fu2018dual, @article{fu2018dual,
title={Dual Attention Network for Scene Segmentation}, title={Dual Attention Network for Scene Segmentation},
@ -13,6 +20,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

173
configs/danet/danet.yml
View File

@ -1,292 +1,301 @@
Collections: Collections:
- Metadata: - Name: danet
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20K - ADE20K
- Pascal VOC 2012 + Aug - Pascal VOC 2012 + Aug
Name: danet Paper:
URL: https://arxiv.org/abs/1809.02983
Title: Dual Attention Network for Scene Segmentation
README: configs/danet/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
Version: v0.17.0
Converted From:
Code: https://github.com/junfu1115/DANet/
Models: Models:
- Config: configs/danet/danet_r50-d8_512x1024_40k_cityscapes.py - Name: danet_r50-d8_512x1024_40k_cityscapes
In Collection: danet In Collection: danet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 375.94
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 375.94
lr schd: 40000
memory (GB): 7.4 memory (GB): 7.4
Name: danet_r50-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.74 mIoU: 78.74
Task: Semantic Segmentation Config: configs/danet/danet_r50-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324-c0dbfa5f.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324-c0dbfa5f.pth
- Config: configs/danet/danet_r101-d8_512x1024_40k_cityscapes.py - Name: danet_r101-d8_512x1024_40k_cityscapes
In Collection: danet In Collection: danet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 502.51
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 502.51
lr schd: 40000
memory (GB): 10.9 memory (GB): 10.9
Name: danet_r101-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.52 mIoU: 80.52
Task: Semantic Segmentation Config: configs/danet/danet_r101-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831-c57a7157.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831-c57a7157.pth
- Config: configs/danet/danet_r50-d8_769x769_40k_cityscapes.py - Name: danet_r50-d8_769x769_40k_cityscapes
In Collection: danet In Collection: danet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 641.03
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 641.03
lr schd: 40000
memory (GB): 8.8 memory (GB): 8.8
Name: danet_r50-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.88 mIoU: 78.88
mIoU(ms+flip): 80.62 mIoU(ms+flip): 80.62
Task: Semantic Segmentation Config: configs/danet/danet_r50-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703-76681c60.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703-76681c60.pth
- Config: configs/danet/danet_r101-d8_769x769_40k_cityscapes.py - Name: danet_r101-d8_769x769_40k_cityscapes
In Collection: danet In Collection: danet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 934.58
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 934.58
lr schd: 40000
memory (GB): 12.8 memory (GB): 12.8
Name: danet_r101-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.88 mIoU: 79.88
mIoU(ms+flip): 81.47 mIoU(ms+flip): 81.47
Task: Semantic Segmentation Config: configs/danet/danet_r101-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717-dcb7fd4e.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717-dcb7fd4e.pth
- Config: configs/danet/danet_r50-d8_512x1024_80k_cityscapes.py - Name: danet_r50-d8_512x1024_80k_cityscapes
In Collection: danet In Collection: danet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: danet_r50-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.34 mIoU: 79.34
Task: Semantic Segmentation Config: configs/danet/danet_r50-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029-2bfa2293.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029-2bfa2293.pth
- Config: configs/danet/danet_r101-d8_512x1024_80k_cityscapes.py - Name: danet_r101-d8_512x1024_80k_cityscapes
In Collection: danet In Collection: danet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: danet_r101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.41 mIoU: 80.41
Task: Semantic Segmentation Config: configs/danet/danet_r101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918-955e6350.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918-955e6350.pth
- Config: configs/danet/danet_r50-d8_769x769_80k_cityscapes.py - Name: danet_r50-d8_769x769_80k_cityscapes
In Collection: danet In Collection: danet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: danet_r50-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.27 mIoU: 79.27
mIoU(ms+flip): 80.96 mIoU(ms+flip): 80.96
Task: Semantic Segmentation Config: configs/danet/danet_r50-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954-495689b4.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954-495689b4.pth
- Config: configs/danet/danet_r101-d8_769x769_80k_cityscapes.py - Name: danet_r101-d8_769x769_80k_cityscapes
In Collection: danet In Collection: danet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: danet_r101-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.47 mIoU: 80.47
mIoU(ms+flip): 82.02 mIoU(ms+flip): 82.02
Task: Semantic Segmentation Config: configs/danet/danet_r101-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918-f3a929e7.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918-f3a929e7.pth
- Config: configs/danet/danet_r50-d8_512x512_80k_ade20k.py - Name: danet_r50-d8_512x512_80k_ade20k
In Collection: danet In Collection: danet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 47.17
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 47.17
lr schd: 80000
memory (GB): 11.5 memory (GB): 11.5
Name: danet_r50-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 41.66 mIoU: 41.66
mIoU(ms+flip): 42.9 mIoU(ms+flip): 42.9
Task: Semantic Segmentation Config: configs/danet/danet_r50-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125-edb18e08.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125-edb18e08.pth
- Config: configs/danet/danet_r101-d8_512x512_80k_ade20k.py - Name: danet_r101-d8_512x512_80k_ade20k
In Collection: danet In Collection: danet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 70.52
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 70.52
lr schd: 80000
memory (GB): 15.0 memory (GB): 15.0
Name: danet_r101-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 43.64 mIoU: 43.64
mIoU(ms+flip): 45.19 mIoU(ms+flip): 45.19
Task: Semantic Segmentation Config: configs/danet/danet_r101-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126-d0357c73.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126-d0357c73.pth
- Config: configs/danet/danet_r50-d8_512x512_160k_ade20k.py - Name: danet_r50-d8_512x512_160k_ade20k
In Collection: danet In Collection: danet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: danet_r50-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.45 mIoU: 42.45
mIoU(ms+flip): 43.25 mIoU(ms+flip): 43.25
Task: Semantic Segmentation Config: configs/danet/danet_r50-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340-9cb35dcd.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340-9cb35dcd.pth
- Config: configs/danet/danet_r101-d8_512x512_160k_ade20k.py - Name: danet_r101-d8_512x512_160k_ade20k
In Collection: danet In Collection: danet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: danet_r101-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 44.17 mIoU: 44.17
mIoU(ms+flip): 45.02 mIoU(ms+flip): 45.02
Task: Semantic Segmentation Config: configs/danet/danet_r101-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348-23bf12f9.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348-23bf12f9.pth
- Config: configs/danet/danet_r50-d8_512x512_20k_voc12aug.py - Name: danet_r50-d8_512x512_20k_voc12aug
In Collection: danet In Collection: danet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 47.76
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 47.76
lr schd: 20000
memory (GB): 6.5 memory (GB): 6.5
Name: danet_r50-d8_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 74.45 mIoU: 74.45
mIoU(ms+flip): 75.69 mIoU(ms+flip): 75.69
Task: Semantic Segmentation Config: configs/danet/danet_r50-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026-9e9e3ab3.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026-9e9e3ab3.pth
- Config: configs/danet/danet_r101-d8_512x512_20k_voc12aug.py - Name: danet_r101-d8_512x512_20k_voc12aug
In Collection: danet In Collection: danet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 72.67
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 72.67
lr schd: 20000
memory (GB): 9.9 memory (GB): 9.9
Name: danet_r101-d8_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 76.02 mIoU: 76.02
mIoU(ms+flip): 77.23 mIoU(ms+flip): 77.23
Task: Semantic Segmentation Config: configs/danet/danet_r101-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026-d48d23b2.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026-d48d23b2.pth
- Config: configs/danet/danet_r50-d8_512x512_40k_voc12aug.py - Name: danet_r50-d8_512x512_40k_voc12aug
In Collection: danet In Collection: danet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: danet_r50-d8_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 76.37 mIoU: 76.37
mIoU(ms+flip): 77.29 mIoU(ms+flip): 77.29
Task: Semantic Segmentation Config: configs/danet/danet_r50-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526-426e3a64.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526-426e3a64.pth
- Config: configs/danet/danet_r101-d8_512x512_40k_voc12aug.py - Name: danet_r101-d8_512x512_40k_voc12aug
In Collection: danet In Collection: danet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: danet_r101-d8_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 76.51 mIoU: 76.51
mIoU(ms+flip): 77.32 mIoU(ms+flip): 77.32
Task: Semantic Segmentation Config: configs/danet/danet_r101-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031-788e232a.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031-788e232a.pth

9
configs/deeplabv3/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/tensorflow/models/tree/master/research/deeplab">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1706.05587">DeepLabV3 (ArXiv'2017)</a></summary>
```latext ```latext
@article{chen2017rethinking, @article{chen2017rethinking,
title={Rethinking atrous convolution for semantic image segmentation}, title={Rethinking atrous convolution for semantic image segmentation},
@ -13,6 +20,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
:::{note} :::{note}

415
configs/deeplabv3/deeplabv3.yml
View File

@ -1,5 +1,6 @@
Collections: Collections:
- Metadata: - Name: deeplabv3
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20K - ADE20K
@ -8,719 +9,727 @@ Collections:
- Pascal Context 59 - Pascal Context 59
- COCO-Stuff 10k - COCO-Stuff 10k
- COCO-Stuff 164k - COCO-Stuff 164k
Name: deeplabv3 Paper:
URL: https://arxiv.org/abs/1706.05587
Title: Rethinking atrous convolution for semantic image segmentation
README: configs/deeplabv3/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/aspp_head.py#L54
Version: v0.17.0
Converted From:
Code: https://github.com/tensorflow/models/tree/master/research/deeplab
Models: Models:
- Config: configs/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes.py - Name: deeplabv3_r50-d8_512x1024_40k_cityscapes
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 389.11
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 389.11
lr schd: 40000
memory (GB): 6.1 memory (GB): 6.1
Name: deeplabv3_r50-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.09 mIoU: 79.09
mIoU(ms+flip): 80.45 mIoU(ms+flip): 80.45
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes/deeplabv3_r50-d8_512x1024_40k_cityscapes_20200605_022449-acadc2f8.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes/deeplabv3_r50-d8_512x1024_40k_cityscapes_20200605_022449-acadc2f8.pth
- Config: configs/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes.py - Name: deeplabv3_r101-d8_512x1024_40k_cityscapes
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 520.83
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 520.83
lr schd: 40000
memory (GB): 9.6 memory (GB): 9.6
Name: deeplabv3_r101-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.12 mIoU: 77.12
mIoU(ms+flip): 79.61 mIoU(ms+flip): 79.61
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes/deeplabv3_r101-d8_512x1024_40k_cityscapes_20200605_012241-7fd3f799.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes/deeplabv3_r101-d8_512x1024_40k_cityscapes_20200605_012241-7fd3f799.pth
- Config: configs/deeplabv3/deeplabv3_r50-d8_769x769_40k_cityscapes.py - Name: deeplabv3_r50-d8_769x769_40k_cityscapes
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 900.9
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 900.9
lr schd: 40000
memory (GB): 6.9 memory (GB): 6.9
Name: deeplabv3_r50-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.58 mIoU: 78.58
mIoU(ms+flip): 79.89 mIoU(ms+flip): 79.89
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r50-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_40k_cityscapes/deeplabv3_r50-d8_769x769_40k_cityscapes_20200606_113723-7eda553c.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_40k_cityscapes/deeplabv3_r50-d8_769x769_40k_cityscapes_20200606_113723-7eda553c.pth
- Config: configs/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes.py - Name: deeplabv3_r101-d8_769x769_40k_cityscapes
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 1204.82
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 1204.82
lr schd: 40000
memory (GB): 10.9 memory (GB): 10.9
Name: deeplabv3_r101-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.27 mIoU: 79.27
mIoU(ms+flip): 80.11 mIoU(ms+flip): 80.11
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes/deeplabv3_r101-d8_769x769_40k_cityscapes_20200606_113809-c64f889f.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes/deeplabv3_r101-d8_769x769_40k_cityscapes_20200606_113809-c64f889f.pth
- Config: configs/deeplabv3/deeplabv3_r18-d8_512x1024_80k_cityscapes.py - Name: deeplabv3_r18-d8_512x1024_80k_cityscapes
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-18-D8 backbone: R-18-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 72.57
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 72.57
lr schd: 80000
memory (GB): 1.7 memory (GB): 1.7
Name: deeplabv3_r18-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 76.7 mIoU: 76.7
mIoU(ms+flip): 78.27 mIoU(ms+flip): 78.27
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r18-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_512x1024_80k_cityscapes/deeplabv3_r18-d8_512x1024_80k_cityscapes_20201225_021506-23dffbe2.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_512x1024_80k_cityscapes/deeplabv3_r18-d8_512x1024_80k_cityscapes_20201225_021506-23dffbe2.pth
- Config: configs/deeplabv3/deeplabv3_r50-d8_512x1024_80k_cityscapes.py - Name: deeplabv3_r50-d8_512x1024_80k_cityscapes
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: deeplabv3_r50-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.32 mIoU: 79.32
mIoU(ms+flip): 80.57 mIoU(ms+flip): 80.57
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r50-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_80k_cityscapes/deeplabv3_r50-d8_512x1024_80k_cityscapes_20200606_113404-b92cfdd4.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_80k_cityscapes/deeplabv3_r50-d8_512x1024_80k_cityscapes_20200606_113404-b92cfdd4.pth
- Config: configs/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes.py - Name: deeplabv3_r101-d8_512x1024_80k_cityscapes
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: deeplabv3_r101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.2 mIoU: 80.2
mIoU(ms+flip): 81.21 mIoU(ms+flip): 81.21
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes/deeplabv3_r101-d8_512x1024_80k_cityscapes_20200606_113503-9e428899.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes/deeplabv3_r101-d8_512x1024_80k_cityscapes_20200606_113503-9e428899.pth
- Config: configs/deeplabv3/deeplabv3_r18-d8_769x769_80k_cityscapes.py - Name: deeplabv3_r18-d8_769x769_80k_cityscapes
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-18-D8 backbone: R-18-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 180.18
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 180.18
lr schd: 80000
memory (GB): 1.9 memory (GB): 1.9
Name: deeplabv3_r18-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 76.6 mIoU: 76.6
mIoU(ms+flip): 78.26 mIoU(ms+flip): 78.26
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r18-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_769x769_80k_cityscapes/deeplabv3_r18-d8_769x769_80k_cityscapes_20201225_021506-6452126a.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18-d8_769x769_80k_cityscapes/deeplabv3_r18-d8_769x769_80k_cityscapes_20201225_021506-6452126a.pth
- Config: configs/deeplabv3/deeplabv3_r50-d8_769x769_80k_cityscapes.py - Name: deeplabv3_r50-d8_769x769_80k_cityscapes
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: deeplabv3_r50-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.89 mIoU: 79.89
mIoU(ms+flip): 81.06 mIoU(ms+flip): 81.06
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r50-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_80k_cityscapes/deeplabv3_r50-d8_769x769_80k_cityscapes_20200606_221338-788d6228.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_80k_cityscapes/deeplabv3_r50-d8_769x769_80k_cityscapes_20200606_221338-788d6228.pth
- Config: configs/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes.py - Name: deeplabv3_r101-d8_769x769_80k_cityscapes
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: deeplabv3_r101-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.67 mIoU: 79.67
mIoU(ms+flip): 80.81 mIoU(ms+flip): 80.81
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes/deeplabv3_r101-d8_769x769_80k_cityscapes_20200607_013353-60e95418.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes/deeplabv3_r101-d8_769x769_80k_cityscapes_20200607_013353-60e95418.pth
- Config: configs/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes.py - Name: deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101-D16-MG124 backbone: R-101-D16-MG124
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.36 mIoU: 78.36
mIoU(ms+flip): 79.84 mIoU(ms+flip): 79.84
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes_20200908_005644-57bb8425.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes_20200908_005644-57bb8425.pth
- Config: configs/deeplabv3/deeplabv3_r18b-d8_512x1024_80k_cityscapes.py - Name: deeplabv3_r18b-d8_512x1024_80k_cityscapes
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-18b-D8 backbone: R-18b-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 71.79
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 71.79
lr schd: 80000
memory (GB): 1.6 memory (GB): 1.6
Name: deeplabv3_r18b-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 76.26 mIoU: 76.26
mIoU(ms+flip): 77.88 mIoU(ms+flip): 77.88
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r18b-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_512x1024_80k_cityscapes/deeplabv3_r18b-d8_512x1024_80k_cityscapes_20201225_094144-46040cef.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_512x1024_80k_cityscapes/deeplabv3_r18b-d8_512x1024_80k_cityscapes_20201225_094144-46040cef.pth
- Config: configs/deeplabv3/deeplabv3_r50b-d8_512x1024_80k_cityscapes.py - Name: deeplabv3_r50b-d8_512x1024_80k_cityscapes
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-50b-D8 backbone: R-50b-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 364.96
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 364.96
lr schd: 80000
memory (GB): 6.0 memory (GB): 6.0
Name: deeplabv3_r50b-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.63 mIoU: 79.63
mIoU(ms+flip): 80.98 mIoU(ms+flip): 80.98
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r50b-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_512x1024_80k_cityscapes/deeplabv3_r50b-d8_512x1024_80k_cityscapes_20201225_155148-ec368954.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_512x1024_80k_cityscapes/deeplabv3_r50b-d8_512x1024_80k_cityscapes_20201225_155148-ec368954.pth
- Config: configs/deeplabv3/deeplabv3_r101b-d8_512x1024_80k_cityscapes.py - Name: deeplabv3_r101b-d8_512x1024_80k_cityscapes
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101b-D8 backbone: R-101b-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 552.49
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 552.49
lr schd: 80000
memory (GB): 9.5 memory (GB): 9.5
Name: deeplabv3_r101b-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.01 mIoU: 80.01
mIoU(ms+flip): 81.21 mIoU(ms+flip): 81.21
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101b-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_512x1024_80k_cityscapes/deeplabv3_r101b-d8_512x1024_80k_cityscapes_20201226_171821-8fd49503.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_512x1024_80k_cityscapes/deeplabv3_r101b-d8_512x1024_80k_cityscapes_20201226_171821-8fd49503.pth
- Config: configs/deeplabv3/deeplabv3_r18b-d8_769x769_80k_cityscapes.py - Name: deeplabv3_r18b-d8_769x769_80k_cityscapes
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-18b-D8 backbone: R-18b-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 172.71
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 172.71
lr schd: 80000
memory (GB): 1.8 memory (GB): 1.8
Name: deeplabv3_r18b-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 76.63 mIoU: 76.63
mIoU(ms+flip): 77.51 mIoU(ms+flip): 77.51
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r18b-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_769x769_80k_cityscapes/deeplabv3_r18b-d8_769x769_80k_cityscapes_20201225_094144-fdc985d9.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r18b-d8_769x769_80k_cityscapes/deeplabv3_r18b-d8_769x769_80k_cityscapes_20201225_094144-fdc985d9.pth
- Config: configs/deeplabv3/deeplabv3_r50b-d8_769x769_80k_cityscapes.py - Name: deeplabv3_r50b-d8_769x769_80k_cityscapes
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-50b-D8 backbone: R-50b-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 862.07
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 862.07
lr schd: 80000
memory (GB): 6.8 memory (GB): 6.8
Name: deeplabv3_r50b-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.8 mIoU: 78.8
mIoU(ms+flip): 80.27 mIoU(ms+flip): 80.27
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r50b-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_769x769_80k_cityscapes/deeplabv3_r50b-d8_769x769_80k_cityscapes_20201225_155404-87fb0cf4.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50b-d8_769x769_80k_cityscapes/deeplabv3_r50b-d8_769x769_80k_cityscapes_20201225_155404-87fb0cf4.pth
- Config: configs/deeplabv3/deeplabv3_r101b-d8_769x769_80k_cityscapes.py - Name: deeplabv3_r101b-d8_769x769_80k_cityscapes
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101b-D8 backbone: R-101b-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 1219.51
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 1219.51
lr schd: 80000
memory (GB): 10.7 memory (GB): 10.7
Name: deeplabv3_r101b-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.41 mIoU: 79.41
mIoU(ms+flip): 80.73 mIoU(ms+flip): 80.73
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101b-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_769x769_80k_cityscapes/deeplabv3_r101b-d8_769x769_80k_cityscapes_20201226_190843-9142ee57.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101b-d8_769x769_80k_cityscapes/deeplabv3_r101b-d8_769x769_80k_cityscapes_20201226_190843-9142ee57.pth
- Config: configs/deeplabv3/deeplabv3_r50-d8_512x512_80k_ade20k.py - Name: deeplabv3_r50-d8_512x512_80k_ade20k
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 67.75
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 67.75
lr schd: 80000
memory (GB): 8.9 memory (GB): 8.9
Name: deeplabv3_r50-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.42 mIoU: 42.42
mIoU(ms+flip): 43.28 mIoU(ms+flip): 43.28
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r50-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_80k_ade20k/deeplabv3_r50-d8_512x512_80k_ade20k_20200614_185028-0bb3f844.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_80k_ade20k/deeplabv3_r50-d8_512x512_80k_ade20k_20200614_185028-0bb3f844.pth
- Config: configs/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k.py - Name: deeplabv3_r101-d8_512x512_80k_ade20k
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 98.62
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 98.62
lr schd: 80000
memory (GB): 12.4 memory (GB): 12.4
Name: deeplabv3_r101-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 44.08 mIoU: 44.08
mIoU(ms+flip): 45.19 mIoU(ms+flip): 45.19
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k/deeplabv3_r101-d8_512x512_80k_ade20k_20200615_021256-d89c7fa4.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k/deeplabv3_r101-d8_512x512_80k_ade20k_20200615_021256-d89c7fa4.pth
- Config: configs/deeplabv3/deeplabv3_r50-d8_512x512_160k_ade20k.py - Name: deeplabv3_r50-d8_512x512_160k_ade20k
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: deeplabv3_r50-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.66 mIoU: 42.66
mIoU(ms+flip): 44.09 mIoU(ms+flip): 44.09
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r50-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_160k_ade20k/deeplabv3_r50-d8_512x512_160k_ade20k_20200615_123227-5d0ee427.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_160k_ade20k/deeplabv3_r50-d8_512x512_160k_ade20k_20200615_123227-5d0ee427.pth
- Config: configs/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k.py - Name: deeplabv3_r101-d8_512x512_160k_ade20k
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: deeplabv3_r101-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 45.0 mIoU: 45.0
mIoU(ms+flip): 46.66 mIoU(ms+flip): 46.66
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k/deeplabv3_r101-d8_512x512_160k_ade20k_20200615_105816-b1f72b3b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k/deeplabv3_r101-d8_512x512_160k_ade20k_20200615_105816-b1f72b3b.pth
- Config: configs/deeplabv3/deeplabv3_r50-d8_512x512_20k_voc12aug.py - Name: deeplabv3_r50-d8_512x512_20k_voc12aug
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 72.05
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 72.05
lr schd: 20000
memory (GB): 6.1 memory (GB): 6.1
Name: deeplabv3_r50-d8_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 76.17 mIoU: 76.17
mIoU(ms+flip): 77.42 mIoU(ms+flip): 77.42
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r50-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_20k_voc12aug/deeplabv3_r50-d8_512x512_20k_voc12aug_20200617_010906-596905ef.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_20k_voc12aug/deeplabv3_r50-d8_512x512_20k_voc12aug_20200617_010906-596905ef.pth
- Config: configs/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug.py - Name: deeplabv3_r101-d8_512x512_20k_voc12aug
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 101.94
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 101.94
lr schd: 20000
memory (GB): 9.6 memory (GB): 9.6
Name: deeplabv3_r101-d8_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 78.7 mIoU: 78.7
mIoU(ms+flip): 79.95 mIoU(ms+flip): 79.95
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug/deeplabv3_r101-d8_512x512_20k_voc12aug_20200617_010932-8d13832f.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug/deeplabv3_r101-d8_512x512_20k_voc12aug_20200617_010932-8d13832f.pth
- Config: configs/deeplabv3/deeplabv3_r50-d8_512x512_40k_voc12aug.py - Name: deeplabv3_r50-d8_512x512_40k_voc12aug
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: deeplabv3_r50-d8_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 77.68 mIoU: 77.68
mIoU(ms+flip): 78.78 mIoU(ms+flip): 78.78
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r50-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_40k_voc12aug/deeplabv3_r50-d8_512x512_40k_voc12aug_20200613_161546-2ae96e7e.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_40k_voc12aug/deeplabv3_r50-d8_512x512_40k_voc12aug_20200613_161546-2ae96e7e.pth
- Config: configs/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug.py - Name: deeplabv3_r101-d8_512x512_40k_voc12aug
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: deeplabv3_r101-d8_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 77.92 mIoU: 77.92
mIoU(ms+flip): 79.18 mIoU(ms+flip): 79.18
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug/deeplabv3_r101-d8_512x512_40k_voc12aug_20200613_161432-0017d784.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug/deeplabv3_r101-d8_512x512_40k_voc12aug_20200613_161432-0017d784.pth
- Config: configs/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context.py - Name: deeplabv3_r101-d8_480x480_40k_pascal_context
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (480,480) crop size: (480,480)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 141.04
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (480,480) resolution: (480,480)
value: 141.04
lr schd: 40000
memory (GB): 9.2 memory (GB): 9.2
Name: deeplabv3_r101-d8_480x480_40k_pascal_context
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal Context Dataset: Pascal Context
Metrics: Metrics:
mIoU: 46.55 mIoU: 46.55
mIoU(ms+flip): 47.81 mIoU(ms+flip): 47.81
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context/deeplabv3_r101-d8_480x480_40k_pascal_context_20200911_204118-1aa27336.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context/deeplabv3_r101-d8_480x480_40k_pascal_context_20200911_204118-1aa27336.pth
- Config: configs/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context.py - Name: deeplabv3_r101-d8_480x480_80k_pascal_context
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (480,480) crop size: (480,480)
lr schd: 80000 lr schd: 80000
Name: deeplabv3_r101-d8_480x480_80k_pascal_context
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal Context Dataset: Pascal Context
Metrics: Metrics:
mIoU: 46.42 mIoU: 46.42
mIoU(ms+flip): 47.53 mIoU(ms+flip): 47.53
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context/deeplabv3_r101-d8_480x480_80k_pascal_context_20200911_170155-2a21fff3.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context/deeplabv3_r101-d8_480x480_80k_pascal_context_20200911_170155-2a21fff3.pth
- Config: configs/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context_59.py - Name: deeplabv3_r101-d8_480x480_40k_pascal_context_59
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (480,480) crop size: (480,480)
lr schd: 40000 lr schd: 40000
Name: deeplabv3_r101-d8_480x480_40k_pascal_context_59
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal Context 59 Dataset: Pascal Context 59
Metrics: Metrics:
mIoU: 52.61 mIoU: 52.61
mIoU(ms+flip): 54.28 mIoU(ms+flip): 54.28
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context_59.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context_59/deeplabv3_r101-d8_480x480_40k_pascal_context_59_20210416_110332-cb08ea46.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context_59/deeplabv3_r101-d8_480x480_40k_pascal_context_59_20210416_110332-cb08ea46.pth
- Config: configs/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context_59.py - Name: deeplabv3_r101-d8_480x480_80k_pascal_context_59
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (480,480) crop size: (480,480)
lr schd: 80000 lr schd: 80000
Name: deeplabv3_r101-d8_480x480_80k_pascal_context_59
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal Context 59 Dataset: Pascal Context 59
Metrics: Metrics:
mIoU: 52.46 mIoU: 52.46
mIoU(ms+flip): 54.09 mIoU(ms+flip): 54.09
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context_59.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context_59/deeplabv3_r101-d8_480x480_80k_pascal_context_59_20210416_113002-26303993.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context_59/deeplabv3_r101-d8_480x480_80k_pascal_context_59_20210416_113002-26303993.pth
- Config: configs/deeplabv3/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k.py - Name: deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 92.59
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 92.59
lr schd: 20000
memory (GB): 9.6 memory (GB): 9.6
Name: deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 10k Dataset: COCO-Stuff 10k
Metrics: Metrics:
mIoU: 34.66 mIoU: 34.66
mIoU(ms+flip): 36.08 mIoU(ms+flip): 36.08
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025-b35f789d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025-b35f789d.pth
- Config: configs/deeplabv3/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k.py - Name: deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 114.94
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 114.94
lr schd: 20000
memory (GB): 13.2 memory (GB): 13.2
Name: deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 10k Dataset: COCO-Stuff 10k
Metrics: Metrics:
mIoU: 37.3 mIoU: 37.3
mIoU(ms+flip): 38.42 mIoU(ms+flip): 38.42
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025-c49752cb.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025-c49752cb.pth
- Config: configs/deeplabv3/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k.py - Name: deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 10k Dataset: COCO-Stuff 10k
Metrics: Metrics:
mIoU: 35.73 mIoU: 35.73
mIoU(ms+flip): 37.09 mIoU(ms+flip): 37.09
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305-dc76f3ff.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305-dc76f3ff.pth
- Config: configs/deeplabv3/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k.py - Name: deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 10k Dataset: COCO-Stuff 10k
Metrics: Metrics:
mIoU: 37.81 mIoU: 37.81
mIoU(ms+flip): 38.8 mIoU(ms+flip): 38.8
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305-636cb433.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305-636cb433.pth
- Config: configs/deeplabv3/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k.py - Name: deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 92.59
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 92.59
lr schd: 80000
memory (GB): 9.6 memory (GB): 9.6
Name: deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 164k Dataset: COCO-Stuff 164k
Metrics: Metrics:
mIoU: 39.38 mIoU: 39.38
mIoU(ms+flip): 40.03 mIoU(ms+flip): 40.03
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k_20210709_163016-88675c24.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k_20210709_163016-88675c24.pth
- Config: configs/deeplabv3/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k.py - Name: deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 114.94
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 114.94
lr schd: 80000
memory (GB): 13.2 memory (GB): 13.2
Name: deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 164k Dataset: COCO-Stuff 164k
Metrics: Metrics:
mIoU: 40.87 mIoU: 40.87
mIoU(ms+flip): 41.5 mIoU(ms+flip): 41.5
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k_20210709_201252-13600dc2.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k_20210709_201252-13600dc2.pth
- Config: configs/deeplabv3/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k.py - Name: deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 164k Dataset: COCO-Stuff 164k
Metrics: Metrics:
mIoU: 41.09 mIoU: 41.09
mIoU(ms+flip): 41.69 mIoU(ms+flip): 41.69
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k_20210709_163016-49f2812b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k_20210709_163016-49f2812b.pth
- Config: configs/deeplabv3/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k.py - Name: deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 164k Dataset: COCO-Stuff 164k
Metrics: Metrics:
mIoU: 41.82 mIoU: 41.82
mIoU(ms+flip): 42.49 mIoU(ms+flip): 42.49
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k_20210709_155402-f035acfd.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k_20210709_155402-f035acfd.pth
- Config: configs/deeplabv3/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k.py - Name: deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 320000 lr schd: 320000
Name: deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 164k Dataset: COCO-Stuff 164k
Metrics: Metrics:
mIoU: 41.37 mIoU: 41.37
mIoU(ms+flip): 42.22 mIoU(ms+flip): 42.22
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k_20210709_155403-51b21115.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k_20210709_155403-51b21115.pth
- Config: configs/deeplabv3/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k.py - Name: deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k
In Collection: deeplabv3 In Collection: deeplabv3
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 320000 lr schd: 320000
Name: deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 164k Dataset: COCO-Stuff 164k
Metrics: Metrics:
mIoU: 42.61 mIoU: 42.61
mIoU(ms+flip): 43.42 mIoU(ms+flip): 43.42
Task: Semantic Segmentation Config: configs/deeplabv3/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k_20210709_155402-3cbca14d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k_20210709_155402-3cbca14d.pth

9
configs/deeplabv3plus/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/tensorflow/models/tree/master/research/deeplab">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1802.02611">DeepLabV3+ (CVPR'2018)</a></summary>
```latex ```latex
@inproceedings{deeplabv3plus2018, @inproceedings{deeplabv3plus2018,
title={Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation}, title={Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation},
@ -13,6 +20,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
:::{note} :::{note}

356
configs/deeplabv3plus/deeplabv3plus.yml
View File

@ -1,574 +1,580 @@
Collections: Collections:
- Metadata: - Name: deeplabv3plus
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20K - ADE20K
- ' Pascal VOC 2012 + Aug' Paper:
- ' Pascal Context' URL: https://arxiv.org/abs/1802.02611
- ' Pascal Context 59' Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Name: deeplabv3plus README: configs/deeplabv3plus/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/sep_aspp_head.py#L30
Version: v0.17.0
Converted From:
Code: https://github.com/tensorflow/models/tree/master/research/deeplab
Models: Models:
- Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes.py - Name: deeplabv3plus_r50-d8_512x1024_40k_cityscapes
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 253.81
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 253.81
lr schd: 40000
memory (GB): 7.5 memory (GB): 7.5
Name: deeplabv3plus_r50-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.61 mIoU: 79.61
mIoU(ms+flip): 81.01 mIoU(ms+flip): 81.01
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes/deeplabv3plus_r50-d8_512x1024_40k_cityscapes_20200605_094610-d222ffcd.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes/deeplabv3plus_r50-d8_512x1024_40k_cityscapes_20200605_094610-d222ffcd.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_40k_cityscapes.py - Name: deeplabv3plus_r101-d8_512x1024_40k_cityscapes
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 384.62
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 384.62
lr schd: 40000
memory (GB): 11.0 memory (GB): 11.0
Name: deeplabv3plus_r101-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.21 mIoU: 80.21
mIoU(ms+flip): 81.82 mIoU(ms+flip): 81.82
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_40k_cityscapes/deeplabv3plus_r101-d8_512x1024_40k_cityscapes_20200605_094614-3769eecf.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_40k_cityscapes/deeplabv3plus_r101-d8_512x1024_40k_cityscapes_20200605_094614-3769eecf.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_769x769_40k_cityscapes.py - Name: deeplabv3plus_r50-d8_769x769_40k_cityscapes
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 581.4
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 581.4
lr schd: 40000
memory (GB): 8.5 memory (GB): 8.5
Name: deeplabv3plus_r50-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.97 mIoU: 78.97
mIoU(ms+flip): 80.46 mIoU(ms+flip): 80.46
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_40k_cityscapes/deeplabv3plus_r50-d8_769x769_40k_cityscapes_20200606_114143-1dcb0e3c.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_40k_cityscapes/deeplabv3plus_r50-d8_769x769_40k_cityscapes_20200606_114143-1dcb0e3c.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_769x769_40k_cityscapes.py - Name: deeplabv3plus_r101-d8_769x769_40k_cityscapes
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 869.57
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 869.57
lr schd: 40000
memory (GB): 12.5 memory (GB): 12.5
Name: deeplabv3plus_r101-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.46 mIoU: 79.46
mIoU(ms+flip): 80.5 mIoU(ms+flip): 80.5
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_40k_cityscapes/deeplabv3plus_r101-d8_769x769_40k_cityscapes_20200606_114304-ff414b9e.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_40k_cityscapes/deeplabv3plus_r101-d8_769x769_40k_cityscapes_20200606_114304-ff414b9e.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_512x1024_80k_cityscapes.py - Name: deeplabv3plus_r18-d8_512x1024_80k_cityscapes
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-18-D8 backbone: R-18-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 70.08
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 70.08
lr schd: 80000
memory (GB): 2.2 memory (GB): 2.2
Name: deeplabv3plus_r18-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 76.89 mIoU: 76.89
mIoU(ms+flip): 78.76 mIoU(ms+flip): 78.76
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x1024_80k_cityscapes/deeplabv3plus_r18-d8_512x1024_80k_cityscapes_20201226_080942-cff257fe.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x1024_80k_cityscapes/deeplabv3plus_r18-d8_512x1024_80k_cityscapes_20201226_080942-cff257fe.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes.py - Name: deeplabv3plus_r50-d8_512x1024_80k_cityscapes
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: deeplabv3plus_r50-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.09 mIoU: 80.09
mIoU(ms+flip): 81.13 mIoU(ms+flip): 81.13
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes/deeplabv3plus_r50-d8_512x1024_80k_cityscapes_20200606_114049-f9fb496d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes/deeplabv3plus_r50-d8_512x1024_80k_cityscapes_20200606_114049-f9fb496d.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes.py - Name: deeplabv3plus_r101-d8_512x1024_80k_cityscapes
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: deeplabv3plus_r101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.97 mIoU: 80.97
mIoU(ms+flip): 82.03 mIoU(ms+flip): 82.03
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143-068fcfe9.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143-068fcfe9.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_769x769_80k_cityscapes.py - Name: deeplabv3plus_r18-d8_769x769_80k_cityscapes
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-18-D8 backbone: R-18-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 174.22
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 174.22
lr schd: 80000
memory (GB): 2.5 memory (GB): 2.5
Name: deeplabv3plus_r18-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 76.26 mIoU: 76.26
mIoU(ms+flip): 77.91 mIoU(ms+flip): 77.91
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_769x769_80k_cityscapes/deeplabv3plus_r18-d8_769x769_80k_cityscapes_20201226_083346-f326e06a.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_769x769_80k_cityscapes/deeplabv3plus_r18-d8_769x769_80k_cityscapes_20201226_083346-f326e06a.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes.py - Name: deeplabv3plus_r50-d8_769x769_80k_cityscapes
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: deeplabv3plus_r50-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.83 mIoU: 79.83
mIoU(ms+flip): 81.48 mIoU(ms+flip): 81.48
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes/deeplabv3plus_r50-d8_769x769_80k_cityscapes_20200606_210233-0e9dfdc4.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes/deeplabv3plus_r50-d8_769x769_80k_cityscapes_20200606_210233-0e9dfdc4.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes.py - Name: deeplabv3plus_r101-d8_769x769_80k_cityscapes
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: deeplabv3plus_r101-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.98 mIoU: 80.98
mIoU(ms+flip): 82.18 mIoU(ms+flip): 82.18
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes/deeplabv3plus_r101-d8_769x769_80k_cityscapes_20200607_000405-a7573d20.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes/deeplabv3plus_r101-d8_769x769_80k_cityscapes_20200607_000405-a7573d20.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes.py - Name: deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-101-D16-MG124 backbone: R-101-D16-MG124
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 133.69
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 133.69
lr schd: 40000
memory (GB): 5.8 memory (GB): 5.8
Name: deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.09 mIoU: 79.09
mIoU(ms+flip): 80.36 mIoU(ms+flip): 80.36
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes_20200908_005644-cf9ce186.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes_20200908_005644-cf9ce186.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes.py - Name: deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-101-D16-MG124 backbone: R-101-D16-MG124
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
memory (GB): 9.9 memory (GB): 9.9
Name: deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.9 mIoU: 79.9
mIoU(ms+flip): 81.33 mIoU(ms+flip): 81.33
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes_20200908_005644-ee6158e0.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes/deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes_20200908_005644-ee6158e0.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes.py - Name: deeplabv3plus_r18b-d8_512x1024_80k_cityscapes
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-18b-D8 backbone: R-18b-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 66.89
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 66.89
lr schd: 80000
memory (GB): 2.1 memory (GB): 2.1
Name: deeplabv3plus_r18b-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 75.87 mIoU: 75.87
mIoU(ms+flip): 77.52 mIoU(ms+flip): 77.52
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes_20201226_090828-e451abd9.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes/deeplabv3plus_r18b-d8_512x1024_80k_cityscapes_20201226_090828-e451abd9.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes.py - Name: deeplabv3plus_r50b-d8_512x1024_80k_cityscapes
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-50b-D8 backbone: R-50b-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 253.81
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 253.81
lr schd: 80000
memory (GB): 7.4 memory (GB): 7.4
Name: deeplabv3plus_r50b-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.28 mIoU: 80.28
mIoU(ms+flip): 81.44 mIoU(ms+flip): 81.44
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes_20201225_213645-a97e4e43.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes/deeplabv3plus_r50b-d8_512x1024_80k_cityscapes_20201225_213645-a97e4e43.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes.py - Name: deeplabv3plus_r101b-d8_512x1024_80k_cityscapes
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-101b-D8 backbone: R-101b-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 384.62
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 384.62
lr schd: 80000
memory (GB): 10.9 memory (GB): 10.9
Name: deeplabv3plus_r101b-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.16 mIoU: 80.16
mIoU(ms+flip): 81.41 mIoU(ms+flip): 81.41
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes_20201226_190843-9c3c93a4.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes/deeplabv3plus_r101b-d8_512x1024_80k_cityscapes_20201226_190843-9c3c93a4.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r18b-d8_769x769_80k_cityscapes.py - Name: deeplabv3plus_r18b-d8_769x769_80k_cityscapes
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-18b-D8 backbone: R-18b-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 167.79
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 167.79
lr schd: 80000
memory (GB): 2.4 memory (GB): 2.4
Name: deeplabv3plus_r18b-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 76.36 mIoU: 76.36
mIoU(ms+flip): 78.24 mIoU(ms+flip): 78.24
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r18b-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_769x769_80k_cityscapes/deeplabv3plus_r18b-d8_769x769_80k_cityscapes_20201226_151312-2c868aff.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18b-d8_769x769_80k_cityscapes/deeplabv3plus_r18b-d8_769x769_80k_cityscapes_20201226_151312-2c868aff.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r50b-d8_769x769_80k_cityscapes.py - Name: deeplabv3plus_r50b-d8_769x769_80k_cityscapes
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-50b-D8 backbone: R-50b-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 581.4
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 581.4
lr schd: 80000
memory (GB): 8.4 memory (GB): 8.4
Name: deeplabv3plus_r50b-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.41 mIoU: 79.41
mIoU(ms+flip): 80.56 mIoU(ms+flip): 80.56
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r50b-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_769x769_80k_cityscapes/deeplabv3plus_r50b-d8_769x769_80k_cityscapes_20201225_224655-8b596d1c.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50b-d8_769x769_80k_cityscapes/deeplabv3plus_r50b-d8_769x769_80k_cityscapes_20201225_224655-8b596d1c.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r101b-d8_769x769_80k_cityscapes.py - Name: deeplabv3plus_r101b-d8_769x769_80k_cityscapes
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-101b-D8 backbone: R-101b-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 909.09
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 909.09
lr schd: 80000
memory (GB): 12.3 memory (GB): 12.3
Name: deeplabv3plus_r101b-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.88 mIoU: 79.88
mIoU(ms+flip): 81.46 mIoU(ms+flip): 81.46
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r101b-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_769x769_80k_cityscapes/deeplabv3plus_r101b-d8_769x769_80k_cityscapes_20201226_205041-227cdf7c.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101b-d8_769x769_80k_cityscapes/deeplabv3plus_r101b-d8_769x769_80k_cityscapes_20201226_205041-227cdf7c.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_ade20k.py - Name: deeplabv3plus_r50-d8_512x512_80k_ade20k
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 47.6
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 47.6
lr schd: 80000
memory (GB): 10.6 memory (GB): 10.6
Name: deeplabv3plus_r50-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.72 mIoU: 42.72
mIoU(ms+flip): 43.75 mIoU(ms+flip): 43.75
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_ade20k/deeplabv3plus_r50-d8_512x512_80k_ade20k_20200614_185028-bf1400d8.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_ade20k/deeplabv3plus_r50-d8_512x512_80k_ade20k_20200614_185028-bf1400d8.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_ade20k.py - Name: deeplabv3plus_r101-d8_512x512_80k_ade20k
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 70.62
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 70.62
lr schd: 80000
memory (GB): 14.1 memory (GB): 14.1
Name: deeplabv3plus_r101-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 44.6 mIoU: 44.6
mIoU(ms+flip): 46.06 mIoU(ms+flip): 46.06
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_ade20k/deeplabv3plus_r101-d8_512x512_80k_ade20k_20200615_014139-d5730af7.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_ade20k/deeplabv3plus_r101-d8_512x512_80k_ade20k_20200615_014139-d5730af7.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_512x512_160k_ade20k.py - Name: deeplabv3plus_r50-d8_512x512_160k_ade20k
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: deeplabv3plus_r50-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 43.95 mIoU: 43.95
mIoU(ms+flip): 44.93 mIoU(ms+flip): 44.93
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_160k_ade20k/deeplabv3plus_r50-d8_512x512_160k_ade20k_20200615_124504-6135c7e0.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_160k_ade20k/deeplabv3plus_r50-d8_512x512_160k_ade20k_20200615_124504-6135c7e0.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_512x512_160k_ade20k.py - Name: deeplabv3plus_r101-d8_512x512_160k_ade20k
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: deeplabv3plus_r101-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 45.47 mIoU: 45.47
mIoU(ms+flip): 46.35 mIoU(ms+flip): 46.35
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_160k_ade20k/deeplabv3plus_r101-d8_512x512_160k_ade20k_20200615_123232-38ed86bb.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_160k_ade20k/deeplabv3plus_r101-d8_512x512_160k_ade20k_20200615_123232-38ed86bb.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_512x512_20k_voc12aug.py - Name: deeplabv3plus_r50-d8_512x512_20k_voc12aug
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 47.62
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 47.62
lr schd: 20000
memory (GB): 7.6 memory (GB): 7.6
Name: deeplabv3plus_r50-d8_512x512_20k_voc12aug
Results: Results:
Dataset: ' Pascal VOC 2012 + Aug' - Task: Semantic Segmentation
Dataset: ADE20K
Metrics: Metrics:
mIoU: 75.93 mIoU: 75.93
mIoU(ms+flip): 77.5 mIoU(ms+flip): 77.5
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_20k_voc12aug/deeplabv3plus_r50-d8_512x512_20k_voc12aug_20200617_102323-aad58ef1.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_20k_voc12aug/deeplabv3plus_r50-d8_512x512_20k_voc12aug_20200617_102323-aad58ef1.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_512x512_20k_voc12aug.py - Name: deeplabv3plus_r101-d8_512x512_20k_voc12aug
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 72.05
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 72.05
lr schd: 20000
memory (GB): 11.0 memory (GB): 11.0
Name: deeplabv3plus_r101-d8_512x512_20k_voc12aug
Results: Results:
Dataset: ' Pascal VOC 2012 + Aug' - Task: Semantic Segmentation
Dataset: ADE20K
Metrics: Metrics:
mIoU: 77.22 mIoU: 77.22
mIoU(ms+flip): 78.59 mIoU(ms+flip): 78.59
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_20k_voc12aug/deeplabv3plus_r101-d8_512x512_20k_voc12aug_20200617_102345-c7ff3d56.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_20k_voc12aug/deeplabv3plus_r101-d8_512x512_20k_voc12aug_20200617_102345-c7ff3d56.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_512x512_40k_voc12aug.py - Name: deeplabv3plus_r50-d8_512x512_40k_voc12aug
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: deeplabv3plus_r50-d8_512x512_40k_voc12aug
Results: Results:
Dataset: ' Pascal VOC 2012 + Aug' - Task: Semantic Segmentation
Dataset: ADE20K
Metrics: Metrics:
mIoU: 76.81 mIoU: 76.81
mIoU(ms+flip): 77.57 mIoU(ms+flip): 77.57
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_40k_voc12aug/deeplabv3plus_r50-d8_512x512_40k_voc12aug_20200613_161759-e1b43aa9.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_40k_voc12aug/deeplabv3plus_r50-d8_512x512_40k_voc12aug_20200613_161759-e1b43aa9.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_512x512_40k_voc12aug.py - Name: deeplabv3plus_r101-d8_512x512_40k_voc12aug
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: deeplabv3plus_r101-d8_512x512_40k_voc12aug
Results: Results:
Dataset: ' Pascal VOC 2012 + Aug' - Task: Semantic Segmentation
Dataset: ADE20K
Metrics: Metrics:
mIoU: 78.62 mIoU: 78.62
mIoU(ms+flip): 79.53 mIoU(ms+flip): 79.53
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_40k_voc12aug/deeplabv3plus_r101-d8_512x512_40k_voc12aug_20200613_205333-faf03387.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_40k_voc12aug/deeplabv3plus_r101-d8_512x512_40k_voc12aug_20200613_205333-faf03387.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context.py - Name: deeplabv3plus_r101-d8_480x480_40k_pascal_context
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (480,480) crop size: (480,480)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 110.01
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (480,480) resolution: (480,480)
value: 110.01
lr schd: 40000
Name: deeplabv3plus_r101-d8_480x480_40k_pascal_context
Results: Results:
Dataset: ' Pascal Context' - Task: Semantic Segmentation
Dataset: ADE20K
Metrics: Metrics:
mIoU: 47.3 mIoU: 47.3
mIoU(ms+flip): 48.47 mIoU(ms+flip): 48.47
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context/deeplabv3plus_r101-d8_480x480_40k_pascal_context_20200911_165459-d3c8a29e.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context/deeplabv3plus_r101-d8_480x480_40k_pascal_context_20200911_165459-d3c8a29e.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context.py - Name: deeplabv3plus_r101-d8_480x480_80k_pascal_context
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (480,480) crop size: (480,480)
lr schd: 80000 lr schd: 80000
Name: deeplabv3plus_r101-d8_480x480_80k_pascal_context
Results: Results:
Dataset: ' Pascal Context' - Task: Semantic Segmentation
Dataset: ADE20K
Metrics: Metrics:
mIoU: 47.23 mIoU: 47.23
mIoU(ms+flip): 48.26 mIoU(ms+flip): 48.26
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context/deeplabv3plus_r101-d8_480x480_80k_pascal_context_20200911_155322-145d3ee8.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context/deeplabv3plus_r101-d8_480x480_80k_pascal_context_20200911_155322-145d3ee8.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59.py - Name: deeplabv3plus_r101-d8_480x480_40k_pascal_context_59
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (480,480) crop size: (480,480)
lr schd: 40000 lr schd: 40000
Name: deeplabv3plus_r101-d8_480x480_40k_pascal_context_59
Results: Results:
Dataset: ' Pascal Context 59' - Task: Semantic Segmentation
Dataset: ADE20K
Metrics: Metrics:
mIoU: 52.86 mIoU: 52.86
mIoU(ms+flip): 54.54 mIoU(ms+flip): 54.54
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59_20210416_111233-ed937f15.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59_20210416_111233-ed937f15.pth
- Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59.py - Name: deeplabv3plus_r101-d8_480x480_80k_pascal_context_59
In Collection: deeplabv3plus In Collection: deeplabv3plus
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (480,480) crop size: (480,480)
lr schd: 80000 lr schd: 80000
Name: deeplabv3plus_r101-d8_480x480_80k_pascal_context_59
Results: Results:
Dataset: ' Pascal Context 59' - Task: Semantic Segmentation
Dataset: ADE20K
Metrics: Metrics:
mIoU: 53.2 mIoU: 53.2
mIoU(ms+flip): 54.67 mIoU(ms+flip): 54.67
Task: Semantic Segmentation Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59_20210416_111127-7ca0331d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59_20210416_111127-7ca0331d.pth

9
configs/dmnet/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/Junjun2016/DMNet">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dm_head.py#L93">Code Snippet</a>
<details>
<summary align="right"><a href="https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf">DMNet (ICCV'2019)</a></summary>
```latex ```latex
@InProceedings{He_2019_ICCV, @InProceedings{He_2019_ICCV,
author = {He, Junjun and Deng, Zhongying and Qiao, Yu}, author = {He, Junjun and Deng, Zhongying and Qiao, Yu},
@ -14,6 +21,8 @@ year = {2019}
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

133
configs/dmnet/dmnet.yml
View File

@ -1,223 +1,232 @@
Collections: Collections:
- Metadata: - Name: dmnet
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20K - ADE20K
Name: dmnet Paper:
URL: https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf
Title: Dynamic Multi-scale Filters for Semantic Segmentation
README: configs/dmnet/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dm_head.py#L93
Version: v0.17.0
Converted From:
Code: https://github.com/Junjun2016/DMNet
Models: Models:
- Config: configs/dmnet/dmnet_r50-d8_512x1024_40k_cityscapes.py - Name: dmnet_r50-d8_512x1024_40k_cityscapes
In Collection: dmnet In Collection: dmnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 273.22
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 273.22
lr schd: 40000
memory (GB): 7.0 memory (GB): 7.0
Name: dmnet_r50-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.78 mIoU: 77.78
mIoU(ms+flip): 79.14 mIoU(ms+flip): 79.14
Task: Semantic Segmentation Config: configs/dmnet/dmnet_r50-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_40k_cityscapes/dmnet_r50-d8_512x1024_40k_cityscapes_20201215_042326-615373cf.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_40k_cityscapes/dmnet_r50-d8_512x1024_40k_cityscapes_20201215_042326-615373cf.pth
- Config: configs/dmnet/dmnet_r101-d8_512x1024_40k_cityscapes.py - Name: dmnet_r101-d8_512x1024_40k_cityscapes
In Collection: dmnet In Collection: dmnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 393.7
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 393.7
lr schd: 40000
memory (GB): 10.6 memory (GB): 10.6
Name: dmnet_r101-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.37 mIoU: 78.37
mIoU(ms+flip): 79.72 mIoU(ms+flip): 79.72
Task: Semantic Segmentation Config: configs/dmnet/dmnet_r101-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_40k_cityscapes/dmnet_r101-d8_512x1024_40k_cityscapes_20201215_043100-8291e976.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_40k_cityscapes/dmnet_r101-d8_512x1024_40k_cityscapes_20201215_043100-8291e976.pth
- Config: configs/dmnet/dmnet_r50-d8_769x769_40k_cityscapes.py - Name: dmnet_r50-d8_769x769_40k_cityscapes
In Collection: dmnet In Collection: dmnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 636.94
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 636.94
lr schd: 40000
memory (GB): 7.9 memory (GB): 7.9
Name: dmnet_r50-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.49 mIoU: 78.49
mIoU(ms+flip): 80.27 mIoU(ms+flip): 80.27
Task: Semantic Segmentation Config: configs/dmnet/dmnet_r50-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_40k_cityscapes/dmnet_r50-d8_769x769_40k_cityscapes_20201215_093706-e7f0e23e.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_40k_cityscapes/dmnet_r50-d8_769x769_40k_cityscapes_20201215_093706-e7f0e23e.pth
- Config: configs/dmnet/dmnet_r101-d8_769x769_40k_cityscapes.py - Name: dmnet_r101-d8_769x769_40k_cityscapes
In Collection: dmnet In Collection: dmnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 990.1
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 990.1
lr schd: 40000
memory (GB): 12.0 memory (GB): 12.0
Name: dmnet_r101-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.62 mIoU: 77.62
mIoU(ms+flip): 78.94 mIoU(ms+flip): 78.94
Task: Semantic Segmentation Config: configs/dmnet/dmnet_r101-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_40k_cityscapes/dmnet_r101-d8_769x769_40k_cityscapes_20201215_081348-a74261f6.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_40k_cityscapes/dmnet_r101-d8_769x769_40k_cityscapes_20201215_081348-a74261f6.pth
- Config: configs/dmnet/dmnet_r50-d8_512x1024_80k_cityscapes.py - Name: dmnet_r50-d8_512x1024_80k_cityscapes
In Collection: dmnet In Collection: dmnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: dmnet_r50-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.07 mIoU: 79.07
mIoU(ms+flip): 80.22 mIoU(ms+flip): 80.22
Task: Semantic Segmentation Config: configs/dmnet/dmnet_r50-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_80k_cityscapes/dmnet_r50-d8_512x1024_80k_cityscapes_20201215_053728-3c8893b9.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_80k_cityscapes/dmnet_r50-d8_512x1024_80k_cityscapes_20201215_053728-3c8893b9.pth
- Config: configs/dmnet/dmnet_r101-d8_512x1024_80k_cityscapes.py - Name: dmnet_r101-d8_512x1024_80k_cityscapes
In Collection: dmnet In Collection: dmnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: dmnet_r101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.64 mIoU: 79.64
mIoU(ms+flip): 80.67 mIoU(ms+flip): 80.67
Task: Semantic Segmentation Config: configs/dmnet/dmnet_r101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_80k_cityscapes/dmnet_r101-d8_512x1024_80k_cityscapes_20201215_031718-fa081cb8.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_80k_cityscapes/dmnet_r101-d8_512x1024_80k_cityscapes_20201215_031718-fa081cb8.pth
- Config: configs/dmnet/dmnet_r50-d8_769x769_80k_cityscapes.py - Name: dmnet_r50-d8_769x769_80k_cityscapes
In Collection: dmnet In Collection: dmnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: dmnet_r50-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.22 mIoU: 79.22
mIoU(ms+flip): 80.55 mIoU(ms+flip): 80.55
Task: Semantic Segmentation Config: configs/dmnet/dmnet_r50-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_80k_cityscapes/dmnet_r50-d8_769x769_80k_cityscapes_20201215_034006-6060840e.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_80k_cityscapes/dmnet_r50-d8_769x769_80k_cityscapes_20201215_034006-6060840e.pth
- Config: configs/dmnet/dmnet_r101-d8_769x769_80k_cityscapes.py - Name: dmnet_r101-d8_769x769_80k_cityscapes
In Collection: dmnet In Collection: dmnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: dmnet_r101-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.19 mIoU: 79.19
mIoU(ms+flip): 80.65 mIoU(ms+flip): 80.65
Task: Semantic Segmentation Config: configs/dmnet/dmnet_r101-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_80k_cityscapes/dmnet_r101-d8_769x769_80k_cityscapes_20201215_082810-7f0de59a.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_80k_cityscapes/dmnet_r101-d8_769x769_80k_cityscapes_20201215_082810-7f0de59a.pth
- Config: configs/dmnet/dmnet_r50-d8_512x512_80k_ade20k.py - Name: dmnet_r50-d8_512x512_80k_ade20k
In Collection: dmnet In Collection: dmnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 47.73
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 47.73
lr schd: 80000
memory (GB): 9.4 memory (GB): 9.4
Name: dmnet_r50-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.37 mIoU: 42.37
mIoU(ms+flip): 43.62 mIoU(ms+flip): 43.62
Task: Semantic Segmentation Config: configs/dmnet/dmnet_r50-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_80k_ade20k/dmnet_r50-d8_512x512_80k_ade20k_20201215_144744-f89092a6.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_80k_ade20k/dmnet_r50-d8_512x512_80k_ade20k_20201215_144744-f89092a6.pth
- Config: configs/dmnet/dmnet_r101-d8_512x512_80k_ade20k.py - Name: dmnet_r101-d8_512x512_80k_ade20k
In Collection: dmnet In Collection: dmnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 72.05
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 72.05
lr schd: 80000
memory (GB): 13.0 memory (GB): 13.0
Name: dmnet_r101-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 45.34 mIoU: 45.34
mIoU(ms+flip): 46.13 mIoU(ms+flip): 46.13
Task: Semantic Segmentation Config: configs/dmnet/dmnet_r101-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_80k_ade20k/dmnet_r101-d8_512x512_80k_ade20k_20201215_104812-bfa45311.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_80k_ade20k/dmnet_r101-d8_512x512_80k_ade20k_20201215_104812-bfa45311.pth
- Config: configs/dmnet/dmnet_r50-d8_512x512_160k_ade20k.py - Name: dmnet_r50-d8_512x512_160k_ade20k
In Collection: dmnet In Collection: dmnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: dmnet_r50-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 43.15 mIoU: 43.15
mIoU(ms+flip): 44.17 mIoU(ms+flip): 44.17
Task: Semantic Segmentation Config: configs/dmnet/dmnet_r50-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_160k_ade20k/dmnet_r50-d8_512x512_160k_ade20k_20201215_115313-025ab3f9.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_160k_ade20k/dmnet_r50-d8_512x512_160k_ade20k_20201215_115313-025ab3f9.pth
- Config: configs/dmnet/dmnet_r101-d8_512x512_160k_ade20k.py - Name: dmnet_r101-d8_512x512_160k_ade20k
In Collection: dmnet In Collection: dmnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: dmnet_r101-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 45.42 mIoU: 45.42
mIoU(ms+flip): 46.76 mIoU(ms+flip): 46.76
Task: Semantic Segmentation Config: configs/dmnet/dmnet_r101-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_160k_ade20k/dmnet_r101-d8_512x512_160k_ade20k_20201215_111145-a0bc02ef.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_160k_ade20k/dmnet_r101-d8_512x512_160k_ade20k_20201215_111145-a0bc02ef.pth

9
configs/dnlnet/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/yinmh17/DNL-Semantic-Segmentation">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dnl_head.py#L88">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/2006.06668">DNLNet (ECCV'2020)</a></summary>
This example is to reproduce ["Disentangled Non-Local Neural Networks"](https://arxiv.org/abs/2006.06668) for semantic segmentation. It is still in progress. This example is to reproduce ["Disentangled Non-Local Neural Networks"](https://arxiv.org/abs/2006.06668) for semantic segmentation. It is still in progress.
## Citation ## Citation
@ -17,6 +24,8 @@ This example is to reproduce ["Disentangled Non-Local Neural Networks"](https://
} }
``` ```
</details>
## Results and models (in progress) ## Results and models (in progress)
### Cityscapes ### Cityscapes

133
configs/dnlnet/dnlnet.yml
View File

@ -1,219 +1,228 @@
Collections: Collections:
- Metadata: - Name: dnlnet
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20K - ADE20K
Name: dnlnet Paper:
URL: https://arxiv.org/abs/2006.06668
Title: Disentangled Non-Local Neural Networks
README: configs/dnlnet/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dnl_head.py#L88
Version: v0.17.0
Converted From:
Code: https://github.com/yinmh17/DNL-Semantic-Segmentation
Models: Models:
- Config: configs/dnlnet/dnl_r50-d8_512x1024_40k_cityscapes.py - Name: dnl_r50-d8_512x1024_40k_cityscapes
In Collection: dnlnet In Collection: dnlnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 390.62
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 390.62
lr schd: 40000
memory (GB): 7.3 memory (GB): 7.3
Name: dnl_r50-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.61 mIoU: 78.61
Task: Semantic Segmentation Config: configs/dnlnet/dnl_r50-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_40k_cityscapes/dnl_r50-d8_512x1024_40k_cityscapes_20200904_233629-53d4ea93.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_40k_cityscapes/dnl_r50-d8_512x1024_40k_cityscapes_20200904_233629-53d4ea93.pth
- Config: configs/dnlnet/dnl_r101-d8_512x1024_40k_cityscapes.py - Name: dnl_r101-d8_512x1024_40k_cityscapes
In Collection: dnlnet In Collection: dnlnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 510.2
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 510.2
lr schd: 40000
memory (GB): 10.9 memory (GB): 10.9
Name: dnl_r101-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.31 mIoU: 78.31
Task: Semantic Segmentation Config: configs/dnlnet/dnl_r101-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_40k_cityscapes/dnl_r101-d8_512x1024_40k_cityscapes_20200904_233629-9928ffef.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_40k_cityscapes/dnl_r101-d8_512x1024_40k_cityscapes_20200904_233629-9928ffef.pth
- Config: configs/dnlnet/dnl_r50-d8_769x769_40k_cityscapes.py - Name: dnl_r50-d8_769x769_40k_cityscapes
In Collection: dnlnet In Collection: dnlnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 666.67
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 666.67
lr schd: 40000
memory (GB): 9.2 memory (GB): 9.2
Name: dnl_r50-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.44 mIoU: 78.44
mIoU(ms+flip): 80.27 mIoU(ms+flip): 80.27
Task: Semantic Segmentation Config: configs/dnlnet/dnl_r50-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_40k_cityscapes/dnl_r50-d8_769x769_40k_cityscapes_20200820_232206-0f283785.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_40k_cityscapes/dnl_r50-d8_769x769_40k_cityscapes_20200820_232206-0f283785.pth
- Config: configs/dnlnet/dnl_r101-d8_769x769_40k_cityscapes.py - Name: dnl_r101-d8_769x769_40k_cityscapes
In Collection: dnlnet In Collection: dnlnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 980.39
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 980.39
lr schd: 40000
memory (GB): 12.6 memory (GB): 12.6
Name: dnl_r101-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 76.39 mIoU: 76.39
mIoU(ms+flip): 77.77 mIoU(ms+flip): 77.77
Task: Semantic Segmentation Config: configs/dnlnet/dnl_r101-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_40k_cityscapes/dnl_r101-d8_769x769_40k_cityscapes_20200820_171256-76c596df.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_40k_cityscapes/dnl_r101-d8_769x769_40k_cityscapes_20200820_171256-76c596df.pth
- Config: configs/dnlnet/dnl_r50-d8_512x1024_80k_cityscapes.py - Name: dnl_r50-d8_512x1024_80k_cityscapes
In Collection: dnlnet In Collection: dnlnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: dnl_r50-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.33 mIoU: 79.33
Task: Semantic Segmentation Config: configs/dnlnet/dnl_r50-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_80k_cityscapes/dnl_r50-d8_512x1024_80k_cityscapes_20200904_233629-58b2f778.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x1024_80k_cityscapes/dnl_r50-d8_512x1024_80k_cityscapes_20200904_233629-58b2f778.pth
- Config: configs/dnlnet/dnl_r101-d8_512x1024_80k_cityscapes.py - Name: dnl_r101-d8_512x1024_80k_cityscapes
In Collection: dnlnet In Collection: dnlnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: dnl_r101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.41 mIoU: 80.41
Task: Semantic Segmentation Config: configs/dnlnet/dnl_r101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_80k_cityscapes/dnl_r101-d8_512x1024_80k_cityscapes_20200904_233629-758e2dd4.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x1024_80k_cityscapes/dnl_r101-d8_512x1024_80k_cityscapes_20200904_233629-758e2dd4.pth
- Config: configs/dnlnet/dnl_r50-d8_769x769_80k_cityscapes.py - Name: dnl_r50-d8_769x769_80k_cityscapes
In Collection: dnlnet In Collection: dnlnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: dnl_r50-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.36 mIoU: 79.36
mIoU(ms+flip): 80.7 mIoU(ms+flip): 80.7
Task: Semantic Segmentation Config: configs/dnlnet/dnl_r50-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_80k_cityscapes/dnl_r50-d8_769x769_80k_cityscapes_20200820_011925-366bc4c7.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_769x769_80k_cityscapes/dnl_r50-d8_769x769_80k_cityscapes_20200820_011925-366bc4c7.pth
- Config: configs/dnlnet/dnl_r101-d8_769x769_80k_cityscapes.py - Name: dnl_r101-d8_769x769_80k_cityscapes
In Collection: dnlnet In Collection: dnlnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: dnl_r101-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.41 mIoU: 79.41
mIoU(ms+flip): 80.68 mIoU(ms+flip): 80.68
Task: Semantic Segmentation Config: configs/dnlnet/dnl_r101-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_80k_cityscapes/dnl_r101-d8_769x769_80k_cityscapes_20200821_051111-95ff84ab.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_769x769_80k_cityscapes/dnl_r101-d8_769x769_80k_cityscapes_20200821_051111-95ff84ab.pth
- Config: configs/dnlnet/dnl_r50-d8_512x512_80k_ade20k.py - Name: dnl_r50-d8_512x512_80k_ade20k
In Collection: dnlnet In Collection: dnlnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 48.4
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 48.4
lr schd: 80000
memory (GB): 8.8 memory (GB): 8.8
Name: dnl_r50-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 41.76 mIoU: 41.76
mIoU(ms+flip): 42.99 mIoU(ms+flip): 42.99
Task: Semantic Segmentation Config: configs/dnlnet/dnl_r50-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_80k_ade20k/dnl_r50-d8_512x512_80k_ade20k_20200826_183354-1cf6e0c1.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_80k_ade20k/dnl_r50-d8_512x512_80k_ade20k_20200826_183354-1cf6e0c1.pth
- Config: configs/dnlnet/dnl_r101-d8_512x512_80k_ade20k.py - Name: dnl_r101-d8_512x512_80k_ade20k
In Collection: dnlnet In Collection: dnlnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 79.74
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 79.74
lr schd: 80000
memory (GB): 12.8 memory (GB): 12.8
Name: dnl_r101-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 43.76 mIoU: 43.76
mIoU(ms+flip): 44.91 mIoU(ms+flip): 44.91
Task: Semantic Segmentation Config: configs/dnlnet/dnl_r101-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_80k_ade20k/dnl_r101-d8_512x512_80k_ade20k_20200826_183354-d820d6ea.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_80k_ade20k/dnl_r101-d8_512x512_80k_ade20k_20200826_183354-d820d6ea.pth
- Config: configs/dnlnet/dnl_r50-d8_512x512_160k_ade20k.py - Name: dnl_r50-d8_512x512_160k_ade20k
In Collection: dnlnet In Collection: dnlnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: dnl_r50-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 41.87 mIoU: 41.87
mIoU(ms+flip): 43.01 mIoU(ms+flip): 43.01
Task: Semantic Segmentation Config: configs/dnlnet/dnl_r50-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_160k_ade20k/dnl_r50-d8_512x512_160k_ade20k_20200826_183350-37837798.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r50-d8_512x512_160k_ade20k/dnl_r50-d8_512x512_160k_ade20k_20200826_183350-37837798.pth
- Config: configs/dnlnet/dnl_r101-d8_512x512_160k_ade20k.py - Name: dnl_r101-d8_512x512_160k_ade20k
In Collection: dnlnet In Collection: dnlnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: dnl_r101-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 44.25 mIoU: 44.25
mIoU(ms+flip): 45.78 mIoU(ms+flip): 45.78
Task: Semantic Segmentation Config: configs/dnlnet/dnl_r101-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_160k_ade20k/dnl_r101-d8_512x512_160k_ade20k_20200826_183350-ed522c61.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dnlnet/dnl_r101-d8_512x512_160k_ade20k/dnl_r101-d8_512x512_160k_ade20k_20200826_183350-ed522c61.pth

9
configs/dpt/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/isl-org/DPT">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dpt_head.py#L215">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/2103.13413">DPT (ArXiv'2021)</a></summary>
```latex ```latex
@article{dosoViTskiy2020, @article{dosoViTskiy2020,
title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale}, title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
@ -20,6 +27,8 @@
} }
``` ```
</details>
## Usage ## Usage
To use other repositories' pre-trained models, it is necessary to convert keys. To use other repositories' pre-trained models, it is necessary to convert keys.

27
configs/dpt/dpt.yml
View File

@ -1,28 +1,37 @@
Collections: Collections:
- Metadata: - Name: dpt
Metadata:
Training Data: Training Data:
- ADE20K - ADE20K
Name: dpt Paper:
URL: https://arxiv.org/abs/2103.13413
Title: Vision Transformer for Dense Prediction
README: configs/dpt/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dpt_head.py#L215
Version: v0.17.0
Converted From:
Code: https://github.com/isl-org/DPT
Models: Models:
- Config: configs/dpt/dpt_vit-b16_512x512_160k_ade20k.py - Name: dpt_vit-b16_512x512_160k_ade20k
In Collection: dpt In Collection: dpt
Metadata: Metadata:
backbone: ViT-B backbone: ViT-B
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 96.06
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 96.06
lr schd: 160000
memory (GB): 8.09 memory (GB): 8.09
Name: dpt_vit-b16_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 46.97 mIoU: 46.97
mIoU(ms+flip): 48.34 mIoU(ms+flip): 48.34
Task: Semantic Segmentation Config: configs/dpt/dpt_vit-b16_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dpt/dpt_vit-b16_512x512_160k_ade20k/dpt_vit-b16_512x512_160k_ade20k-db31cf52.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dpt/dpt_vit-b16_512x512_160k_ade20k/dpt_vit-b16_512x512_160k_ade20k-db31cf52.pth

9
configs/emanet/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://xialipku.github.io/EMANet">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ema_head.py#L80">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1907.13426">EMANet (ICCV'2019)</a></summary>
```latex ```latex
@inproceedings{li2019expectation, @inproceedings{li2019expectation,
title={Expectation-maximization attention networks for semantic segmentation}, title={Expectation-maximization attention networks for semantic segmentation},
@ -14,6 +21,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

69
configs/emanet/emanet.yml
View File

@ -1,94 +1,103 @@
Collections: Collections:
- Metadata: - Name: emanet
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
Name: emanet Paper:
URL: https://arxiv.org/abs/1907.13426
Title: Expectation-Maximization Attention Networks for Semantic Segmentation
README: configs/emanet/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ema_head.py#L80
Version: v0.17.0
Converted From:
Code: https://xialipku.github.io/EMANet
Models: Models:
- Config: configs/emanet/emanet_r50-d8_512x1024_80k_cityscapes.py - Name: emanet_r50-d8_512x1024_80k_cityscapes
In Collection: emanet In Collection: emanet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 218.34
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 218.34
lr schd: 80000
memory (GB): 5.4 memory (GB): 5.4
Name: emanet_r50-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.59 mIoU: 77.59
mIoU(ms+flip): 79.44 mIoU(ms+flip): 79.44
Task: Semantic Segmentation Config: configs/emanet/emanet_r50-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r50-d8_512x1024_80k_cityscapes/emanet_r50-d8_512x1024_80k_cityscapes_20200901_100301-c43fcef1.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r50-d8_512x1024_80k_cityscapes/emanet_r50-d8_512x1024_80k_cityscapes_20200901_100301-c43fcef1.pth
- Config: configs/emanet/emanet_r101-d8_512x1024_80k_cityscapes.py - Name: emanet_r101-d8_512x1024_80k_cityscapes
In Collection: emanet In Collection: emanet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 348.43
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 348.43
lr schd: 80000
memory (GB): 6.2 memory (GB): 6.2
Name: emanet_r101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.1 mIoU: 79.1
mIoU(ms+flip): 81.21 mIoU(ms+flip): 81.21
Task: Semantic Segmentation Config: configs/emanet/emanet_r101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r101-d8_512x1024_80k_cityscapes/emanet_r101-d8_512x1024_80k_cityscapes_20200901_100301-2d970745.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r101-d8_512x1024_80k_cityscapes/emanet_r101-d8_512x1024_80k_cityscapes_20200901_100301-2d970745.pth
- Config: configs/emanet/emanet_r50-d8_769x769_80k_cityscapes.py - Name: emanet_r50-d8_769x769_80k_cityscapes
In Collection: emanet In Collection: emanet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 507.61
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 507.61
lr schd: 80000
memory (GB): 8.9 memory (GB): 8.9
Name: emanet_r50-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.33 mIoU: 79.33
mIoU(ms+flip): 80.49 mIoU(ms+flip): 80.49
Task: Semantic Segmentation Config: configs/emanet/emanet_r50-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r50-d8_769x769_80k_cityscapes/emanet_r50-d8_769x769_80k_cityscapes_20200901_100301-16f8de52.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r50-d8_769x769_80k_cityscapes/emanet_r50-d8_769x769_80k_cityscapes_20200901_100301-16f8de52.pth
- Config: configs/emanet/emanet_r101-d8_769x769_80k_cityscapes.py - Name: emanet_r101-d8_769x769_80k_cityscapes
In Collection: emanet In Collection: emanet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 819.67
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 819.67
lr schd: 80000
memory (GB): 10.1 memory (GB): 10.1
Name: emanet_r101-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.62 mIoU: 79.62
mIoU(ms+flip): 81.0 mIoU(ms+flip): 81.0
Task: Semantic Segmentation Config: configs/emanet/emanet_r101-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r101-d8_769x769_80k_cityscapes/emanet_r101-d8_769x769_80k_cityscapes_20200901_100301-47a324ce.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/emanet/emanet_r101-d8_769x769_80k_cityscapes/emanet_r101-d8_769x769_80k_cityscapes_20200901_100301-47a324ce.pth

9
configs/encnet/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/zhanghang1989/PyTorch-Encoding">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/enc_head.py#L63">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1803.08904">EncNet (CVPR'2018)</a></summary>
```latex ```latex
@InProceedings{Zhang_2018_CVPR, @InProceedings{Zhang_2018_CVPR,
author = {Zhang, Hang and Dana, Kristin and Shi, Jianping and Zhang, Zhongyue and Wang, Xiaogang and Tyagi, Ambrish and Agrawal, Amit}, author = {Zhang, Hang and Dana, Kristin and Shi, Jianping and Zhang, Zhongyue and Wang, Xiaogang and Tyagi, Ambrish and Agrawal, Amit},
@ -14,6 +21,8 @@ year = {2018}
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

133
configs/encnet/encnet.yml
View File

@ -1,223 +1,232 @@
Collections: Collections:
- Metadata: - Name: encnet
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20K - ADE20K
Name: encnet Paper:
URL: https://arxiv.org/abs/1803.08904
Title: Context Encoding for Semantic Segmentation
README: configs/encnet/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/enc_head.py#L63
Version: v0.17.0
Converted From:
Code: https://github.com/zhanghang1989/PyTorch-Encoding
Models: Models:
- Config: configs/encnet/encnet_r50-d8_512x1024_40k_cityscapes.py - Name: encnet_r50-d8_512x1024_40k_cityscapes
In Collection: encnet In Collection: encnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 218.34
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 218.34
lr schd: 40000
memory (GB): 8.6 memory (GB): 8.6
Name: encnet_r50-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 75.67 mIoU: 75.67
mIoU(ms+flip): 77.08 mIoU(ms+flip): 77.08
Task: Semantic Segmentation Config: configs/encnet/encnet_r50-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_40k_cityscapes/encnet_r50-d8_512x1024_40k_cityscapes_20200621_220958-68638a47.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_40k_cityscapes/encnet_r50-d8_512x1024_40k_cityscapes_20200621_220958-68638a47.pth
- Config: configs/encnet/encnet_r101-d8_512x1024_40k_cityscapes.py - Name: encnet_r101-d8_512x1024_40k_cityscapes
In Collection: encnet In Collection: encnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 375.94
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 375.94
lr schd: 40000
memory (GB): 12.1 memory (GB): 12.1
Name: encnet_r101-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 75.81 mIoU: 75.81
mIoU(ms+flip): 77.21 mIoU(ms+flip): 77.21
Task: Semantic Segmentation Config: configs/encnet/encnet_r101-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_40k_cityscapes/encnet_r101-d8_512x1024_40k_cityscapes_20200621_220933-35e0a3e8.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_40k_cityscapes/encnet_r101-d8_512x1024_40k_cityscapes_20200621_220933-35e0a3e8.pth
- Config: configs/encnet/encnet_r50-d8_769x769_40k_cityscapes.py - Name: encnet_r50-d8_769x769_40k_cityscapes
In Collection: encnet In Collection: encnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 549.45
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 549.45
lr schd: 40000
memory (GB): 9.8 memory (GB): 9.8
Name: encnet_r50-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 76.24 mIoU: 76.24
mIoU(ms+flip): 77.85 mIoU(ms+flip): 77.85
Task: Semantic Segmentation Config: configs/encnet/encnet_r50-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_40k_cityscapes/encnet_r50-d8_769x769_40k_cityscapes_20200621_220958-3bcd2884.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_40k_cityscapes/encnet_r50-d8_769x769_40k_cityscapes_20200621_220958-3bcd2884.pth
- Config: configs/encnet/encnet_r101-d8_769x769_40k_cityscapes.py - Name: encnet_r101-d8_769x769_40k_cityscapes
In Collection: encnet In Collection: encnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 793.65
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 793.65
lr schd: 40000
memory (GB): 13.7 memory (GB): 13.7
Name: encnet_r101-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 74.25 mIoU: 74.25
mIoU(ms+flip): 76.25 mIoU(ms+flip): 76.25
Task: Semantic Segmentation Config: configs/encnet/encnet_r101-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_40k_cityscapes/encnet_r101-d8_769x769_40k_cityscapes_20200621_220933-2fafed55.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_40k_cityscapes/encnet_r101-d8_769x769_40k_cityscapes_20200621_220933-2fafed55.pth
- Config: configs/encnet/encnet_r50-d8_512x1024_80k_cityscapes.py - Name: encnet_r50-d8_512x1024_80k_cityscapes
In Collection: encnet In Collection: encnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: encnet_r50-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.94 mIoU: 77.94
mIoU(ms+flip): 79.13 mIoU(ms+flip): 79.13
Task: Semantic Segmentation Config: configs/encnet/encnet_r50-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_80k_cityscapes/encnet_r50-d8_512x1024_80k_cityscapes_20200622_003554-fc5c5624.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x1024_80k_cityscapes/encnet_r50-d8_512x1024_80k_cityscapes_20200622_003554-fc5c5624.pth
- Config: configs/encnet/encnet_r101-d8_512x1024_80k_cityscapes.py - Name: encnet_r101-d8_512x1024_80k_cityscapes
In Collection: encnet In Collection: encnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: encnet_r101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.55 mIoU: 78.55
mIoU(ms+flip): 79.47 mIoU(ms+flip): 79.47
Task: Semantic Segmentation Config: configs/encnet/encnet_r101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_80k_cityscapes/encnet_r101-d8_512x1024_80k_cityscapes_20200622_003555-1de64bec.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x1024_80k_cityscapes/encnet_r101-d8_512x1024_80k_cityscapes_20200622_003555-1de64bec.pth
- Config: configs/encnet/encnet_r50-d8_769x769_80k_cityscapes.py - Name: encnet_r50-d8_769x769_80k_cityscapes
In Collection: encnet In Collection: encnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: encnet_r50-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.44 mIoU: 77.44
mIoU(ms+flip): 78.72 mIoU(ms+flip): 78.72
Task: Semantic Segmentation Config: configs/encnet/encnet_r50-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_80k_cityscapes/encnet_r50-d8_769x769_80k_cityscapes_20200622_003554-55096dcb.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_769x769_80k_cityscapes/encnet_r50-d8_769x769_80k_cityscapes_20200622_003554-55096dcb.pth
- Config: configs/encnet/encnet_r101-d8_769x769_80k_cityscapes.py - Name: encnet_r101-d8_769x769_80k_cityscapes
In Collection: encnet In Collection: encnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: encnet_r101-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 76.1 mIoU: 76.1
mIoU(ms+flip): 76.97 mIoU(ms+flip): 76.97
Task: Semantic Segmentation Config: configs/encnet/encnet_r101-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_80k_cityscapes/encnet_r101-d8_769x769_80k_cityscapes_20200622_003555-470ef79d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_769x769_80k_cityscapes/encnet_r101-d8_769x769_80k_cityscapes_20200622_003555-470ef79d.pth
- Config: configs/encnet/encnet_r50-d8_512x512_80k_ade20k.py - Name: encnet_r50-d8_512x512_80k_ade20k
In Collection: encnet In Collection: encnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 43.84
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 43.84
lr schd: 80000
memory (GB): 10.1 memory (GB): 10.1
Name: encnet_r50-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 39.53 mIoU: 39.53
mIoU(ms+flip): 41.17 mIoU(ms+flip): 41.17
Task: Semantic Segmentation Config: configs/encnet/encnet_r50-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_80k_ade20k/encnet_r50-d8_512x512_80k_ade20k_20200622_042412-44b46b04.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_80k_ade20k/encnet_r50-d8_512x512_80k_ade20k_20200622_042412-44b46b04.pth
- Config: configs/encnet/encnet_r101-d8_512x512_80k_ade20k.py - Name: encnet_r101-d8_512x512_80k_ade20k
In Collection: encnet In Collection: encnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 67.25
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 67.25
lr schd: 80000
memory (GB): 13.6 memory (GB): 13.6
Name: encnet_r101-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.11 mIoU: 42.11
mIoU(ms+flip): 43.61 mIoU(ms+flip): 43.61
Task: Semantic Segmentation Config: configs/encnet/encnet_r101-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_80k_ade20k/encnet_r101-d8_512x512_80k_ade20k_20200622_101128-dd35e237.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_80k_ade20k/encnet_r101-d8_512x512_80k_ade20k_20200622_101128-dd35e237.pth
- Config: configs/encnet/encnet_r50-d8_512x512_160k_ade20k.py - Name: encnet_r50-d8_512x512_160k_ade20k
In Collection: encnet In Collection: encnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: encnet_r50-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 40.1 mIoU: 40.1
mIoU(ms+flip): 41.71 mIoU(ms+flip): 41.71
Task: Semantic Segmentation Config: configs/encnet/encnet_r50-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_160k_ade20k/encnet_r50-d8_512x512_160k_ade20k_20200622_101059-b2db95e0.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r50-d8_512x512_160k_ade20k/encnet_r50-d8_512x512_160k_ade20k_20200622_101059-b2db95e0.pth
- Config: configs/encnet/encnet_r101-d8_512x512_160k_ade20k.py - Name: encnet_r101-d8_512x512_160k_ade20k
In Collection: encnet In Collection: encnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: encnet_r101-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.61 mIoU: 42.61
mIoU(ms+flip): 44.01 mIoU(ms+flip): 44.01
Task: Semantic Segmentation Config: configs/encnet/encnet_r101-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_160k_ade20k/encnet_r101-d8_512x512_160k_ade20k_20200622_073348-7989641f.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/encnet/encnet_r101-d8_512x512_160k_ade20k/encnet_r101-d8_512x512_160k_ade20k_20200622_073348-7989641f.pth

9
configs/fastscnn/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/fast_scnn.py#L272">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1902.04502">Fast-SCNN (ArXiv'2019)</a></summary>
```latex ```latex
@article{poudel2019fast, @article{poudel2019fast,
title={Fast-scnn: Fast semantic segmentation network}, title={Fast-scnn: Fast semantic segmentation network},
@ -13,6 +20,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

25
configs/fastscnn/fastscnn.yml
View File

@ -1,28 +1,35 @@
Collections: Collections:
- Metadata: - Name: fastscnn
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
Name: fastscnn Paper:
URL: https://arxiv.org/abs/1902.04502
Title: Fast-SCNN for Semantic Segmentation
README: configs/fastscnn/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/fast_scnn.py#L272
Version: v0.17.0
Models: Models:
- Config: configs/fastscnn/fast_scnn_lr0.12_8x4_160k_cityscapes.py - Name: fast_scnn_lr0.12_8x4_160k_cityscapes
In Collection: fastscnn In Collection: fastscnn
Metadata: Metadata:
backbone: Fast-SCNN backbone: Fast-SCNN
crop size: (512,1024) crop size: (512,1024)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 17.71
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 17.71
lr schd: 160000
memory (GB): 3.3 memory (GB): 3.3
Name: fast_scnn_lr0.12_8x4_160k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 70.96 mIoU: 70.96
mIoU(ms+flip): 72.65 mIoU(ms+flip): 72.65
Task: Semantic Segmentation Config: configs/fastscnn/fast_scnn_lr0.12_8x4_160k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_lr0.12_8x4_160k_cityscapes/fast_scnn_lr0.12_8x4_160k_cityscapes_20210630_164853-0cec9937.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_lr0.12_8x4_160k_cityscapes/fast_scnn_lr0.12_8x4_160k_cityscapes_20210630_164853-0cec9937.pth

9
configs/fcn/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/BVLC/caffe/wiki/Model-Zoo#fcn">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1411.4038">FCN (CVPR'2015/TPAMI'2017)</a></summary>
```latex ```latex
@article{shelhamer2017fully, @article{shelhamer2017fully,
title={Fully convolutional networks for semantic segmentation}, title={Fully convolutional networks for semantic segmentation},
@ -17,6 +24,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

485
configs/fcn/fcn.yml
View File

File diff suppressed because it is too large Load Diff

9
configs/fp16/README.md
View File

@ -4,6 +4,13 @@
<!-- [OTHERS] --> <!-- [OTHERS] -->
<a href="https://github.com/baidu-research/DeepBench">Official Repo</a>
<a href="https://github.com/open-mmlab/mmcv/blob/v1.3.14/mmcv/runner/hooks/optimizer.py#L134">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1710.03740">Mixed Precision (FP16) Training (ArXiv'2017)</a></summary>
```latex ```latex
@article{micikevicius2017mixed, @article{micikevicius2017mixed,
title={Mixed precision training}, title={Mixed precision training},
@ -13,6 +20,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

69
configs/fp16/fp16.yml
View File

@ -1,90 +1,99 @@
Collections: Collections:
- Metadata: - Name: fp16
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
Name: fp16 Paper:
URL: https://arxiv.org/abs/1710.03740
Title: Mixed Precision Training
README: configs/fp16/README.md
Code:
URL: https://github.com/open-mmlab/mmcv/blob/v1.3.14/mmcv/runner/hooks/optimizer.py#L134
Version: v1.3.14
Converted From:
Code: https://github.com/baidu-research/DeepBench
Models: Models:
- Config: configs/fp16/fcn_r101-d8_512x1024_80k_fp16_cityscapes.py - Name: fcn_r101-d8_512x1024_80k_fp16_cityscapes
In Collection: fp16 In Collection: fp16
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 115.74
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 115.74
lr schd: 80000
memory (GB): 5.37 memory (GB): 5.37
Name: fcn_r101-d8_512x1024_80k_fp16_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 76.8 mIoU: 76.8
Task: Semantic Segmentation Config: configs/fp16/fcn_r101-d8_512x1024_80k_fp16_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fp16/fcn_r101-d8_512x1024_80k_fp16_cityscapes/fcn_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230921-50245227.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fp16/fcn_r101-d8_512x1024_80k_fp16_cityscapes/fcn_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230921-50245227.pth
- Config: configs/fp16/pspnet_r101-d8_512x1024_80k_fp16_cityscapes.py - Name: pspnet_r101-d8_512x1024_80k_fp16_cityscapes
In Collection: fp16 In Collection: fp16
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 114.03
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 114.03
lr schd: 80000
memory (GB): 5.34 memory (GB): 5.34
Name: pspnet_r101-d8_512x1024_80k_fp16_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.46 mIoU: 79.46
Task: Semantic Segmentation Config: configs/fp16/pspnet_r101-d8_512x1024_80k_fp16_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fp16/pspnet_r101-d8_512x1024_80k_fp16_cityscapes/pspnet_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230919-ade37931.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fp16/pspnet_r101-d8_512x1024_80k_fp16_cityscapes/pspnet_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230919-ade37931.pth
- Config: configs/fp16/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes.py - Name: deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes
In Collection: fp16 In Collection: fp16
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 259.07
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 259.07
lr schd: 80000
memory (GB): 5.75 memory (GB): 5.75
Name: deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.48 mIoU: 80.48
Task: Semantic Segmentation Config: configs/fp16/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fp16/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230920-bc86dc84.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fp16/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230920-bc86dc84.pth
- Config: configs/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes.py - Name: deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes
In Collection: fp16 In Collection: fp16
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 127.06
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 127.06
lr schd: 80000
memory (GB): 6.35 memory (GB): 6.35
Name: deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.46 mIoU: 80.46
Task: Semantic Segmentation Config: configs/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230920-cc58bc8d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230920-cc58bc8d.pth

9
configs/gcnet/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/xvjiarui/GCNet">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1904.11492">GCNet (ICCVW'2019/TPAMI'2020)</a></summary>
```latex ```latex
@inproceedings{cao2019gcnet, @inproceedings{cao2019gcnet,
title={Gcnet: Non-local networks meet squeeze-excitation networks and beyond}, title={Gcnet: Non-local networks meet squeeze-excitation networks and beyond},
@ -14,6 +21,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

173
configs/gcnet/gcnet.yml
View File

@ -1,296 +1,305 @@
Collections: Collections:
- Metadata: - Name: gcnet
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20K - ADE20K
- Pascal VOC 2012 + Aug - Pascal VOC 2012 + Aug
Name: gcnet Paper:
URL: https://arxiv.org/abs/1904.11492
Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
README: configs/gcnet/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
Version: v0.17.0
Converted From:
Code: https://github.com/xvjiarui/GCNet
Models: Models:
- Config: configs/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes.py - Name: gcnet_r50-d8_512x1024_40k_cityscapes
In Collection: gcnet In Collection: gcnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 254.45
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 254.45
lr schd: 40000
memory (GB): 5.8 memory (GB): 5.8
Name: gcnet_r50-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.69 mIoU: 77.69
mIoU(ms+flip): 78.56 mIoU(ms+flip): 78.56
Task: Semantic Segmentation Config: configs/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436-4b0fd17b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436-4b0fd17b.pth
- Config: configs/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes.py - Name: gcnet_r101-d8_512x1024_40k_cityscapes
In Collection: gcnet In Collection: gcnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 383.14
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 383.14
lr schd: 40000
memory (GB): 9.2 memory (GB): 9.2
Name: gcnet_r101-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.28 mIoU: 78.28
mIoU(ms+flip): 79.34 mIoU(ms+flip): 79.34
Task: Semantic Segmentation Config: configs/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436-5e62567f.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436-5e62567f.pth
- Config: configs/gcnet/gcnet_r50-d8_769x769_40k_cityscapes.py - Name: gcnet_r50-d8_769x769_40k_cityscapes
In Collection: gcnet In Collection: gcnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 598.8
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 598.8
lr schd: 40000
memory (GB): 6.5 memory (GB): 6.5
Name: gcnet_r50-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.12 mIoU: 78.12
mIoU(ms+flip): 80.09 mIoU(ms+flip): 80.09
Task: Semantic Segmentation Config: configs/gcnet/gcnet_r50-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814-a26f4471.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814-a26f4471.pth
- Config: configs/gcnet/gcnet_r101-d8_769x769_40k_cityscapes.py - Name: gcnet_r101-d8_769x769_40k_cityscapes
In Collection: gcnet In Collection: gcnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 884.96
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 884.96
lr schd: 40000
memory (GB): 10.5 memory (GB): 10.5
Name: gcnet_r101-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.95 mIoU: 78.95
mIoU(ms+flip): 80.71 mIoU(ms+flip): 80.71
Task: Semantic Segmentation Config: configs/gcnet/gcnet_r101-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550-ca4f0a84.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550-ca4f0a84.pth
- Config: configs/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes.py - Name: gcnet_r50-d8_512x1024_80k_cityscapes
In Collection: gcnet In Collection: gcnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: gcnet_r50-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.48 mIoU: 78.48
mIoU(ms+flip): 80.01 mIoU(ms+flip): 80.01
Task: Semantic Segmentation Config: configs/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450-ef8f069b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450-ef8f069b.pth
- Config: configs/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes.py - Name: gcnet_r101-d8_512x1024_80k_cityscapes
In Collection: gcnet In Collection: gcnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: gcnet_r101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.03 mIoU: 79.03
mIoU(ms+flip): 79.84 mIoU(ms+flip): 79.84
Task: Semantic Segmentation Config: configs/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450-778ebf69.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450-778ebf69.pth
- Config: configs/gcnet/gcnet_r50-d8_769x769_80k_cityscapes.py - Name: gcnet_r50-d8_769x769_80k_cityscapes
In Collection: gcnet In Collection: gcnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: gcnet_r50-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.68 mIoU: 78.68
mIoU(ms+flip): 80.66 mIoU(ms+flip): 80.66
Task: Semantic Segmentation Config: configs/gcnet/gcnet_r50-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516-4839565b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516-4839565b.pth
- Config: configs/gcnet/gcnet_r101-d8_769x769_80k_cityscapes.py - Name: gcnet_r101-d8_769x769_80k_cityscapes
In Collection: gcnet In Collection: gcnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: gcnet_r101-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.18 mIoU: 79.18
mIoU(ms+flip): 80.71 mIoU(ms+flip): 80.71
Task: Semantic Segmentation Config: configs/gcnet/gcnet_r101-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628-8e043423.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628-8e043423.pth
- Config: configs/gcnet/gcnet_r50-d8_512x512_80k_ade20k.py - Name: gcnet_r50-d8_512x512_80k_ade20k
In Collection: gcnet In Collection: gcnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 42.77
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 42.77
lr schd: 80000
memory (GB): 8.5 memory (GB): 8.5
Name: gcnet_r50-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 41.47 mIoU: 41.47
mIoU(ms+flip): 42.85 mIoU(ms+flip): 42.85
Task: Semantic Segmentation Config: configs/gcnet/gcnet_r50-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146-91a6da41.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146-91a6da41.pth
- Config: configs/gcnet/gcnet_r101-d8_512x512_80k_ade20k.py - Name: gcnet_r101-d8_512x512_80k_ade20k
In Collection: gcnet In Collection: gcnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 65.79
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 65.79
lr schd: 80000
memory (GB): 12.0 memory (GB): 12.0
Name: gcnet_r101-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.82 mIoU: 42.82
mIoU(ms+flip): 44.54 mIoU(ms+flip): 44.54
Task: Semantic Segmentation Config: configs/gcnet/gcnet_r101-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811-c3fcb6dd.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811-c3fcb6dd.pth
- Config: configs/gcnet/gcnet_r50-d8_512x512_160k_ade20k.py - Name: gcnet_r50-d8_512x512_160k_ade20k
In Collection: gcnet In Collection: gcnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: gcnet_r50-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.37 mIoU: 42.37
mIoU(ms+flip): 43.52 mIoU(ms+flip): 43.52
Task: Semantic Segmentation Config: configs/gcnet/gcnet_r50-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122-d95f3e1f.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122-d95f3e1f.pth
- Config: configs/gcnet/gcnet_r101-d8_512x512_160k_ade20k.py - Name: gcnet_r101-d8_512x512_160k_ade20k
In Collection: gcnet In Collection: gcnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: gcnet_r101-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 43.69 mIoU: 43.69
mIoU(ms+flip): 45.21 mIoU(ms+flip): 45.21
Task: Semantic Segmentation Config: configs/gcnet/gcnet_r101-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406-615528d7.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406-615528d7.pth
- Config: configs/gcnet/gcnet_r50-d8_512x512_20k_voc12aug.py - Name: gcnet_r50-d8_512x512_20k_voc12aug
In Collection: gcnet In Collection: gcnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 42.83
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 42.83
lr schd: 20000
memory (GB): 5.8 memory (GB): 5.8
Name: gcnet_r50-d8_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 76.42 mIoU: 76.42
mIoU(ms+flip): 77.51 mIoU(ms+flip): 77.51
Task: Semantic Segmentation Config: configs/gcnet/gcnet_r50-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701-3cbfdab1.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701-3cbfdab1.pth
- Config: configs/gcnet/gcnet_r101-d8_512x512_20k_voc12aug.py - Name: gcnet_r101-d8_512x512_20k_voc12aug
In Collection: gcnet In Collection: gcnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 67.57
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 67.57
lr schd: 20000
memory (GB): 9.2 memory (GB): 9.2
Name: gcnet_r101-d8_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 77.41 mIoU: 77.41
mIoU(ms+flip): 78.56 mIoU(ms+flip): 78.56
Task: Semantic Segmentation Config: configs/gcnet/gcnet_r101-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713-6c720aa9.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713-6c720aa9.pth
- Config: configs/gcnet/gcnet_r50-d8_512x512_40k_voc12aug.py - Name: gcnet_r50-d8_512x512_40k_voc12aug
In Collection: gcnet In Collection: gcnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: gcnet_r50-d8_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 76.24 mIoU: 76.24
mIoU(ms+flip): 77.63 mIoU(ms+flip): 77.63
Task: Semantic Segmentation Config: configs/gcnet/gcnet_r50-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105-9797336d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105-9797336d.pth
- Config: configs/gcnet/gcnet_r101-d8_512x512_40k_voc12aug.py - Name: gcnet_r101-d8_512x512_40k_voc12aug
In Collection: gcnet In Collection: gcnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: gcnet_r101-d8_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 77.84 mIoU: 77.84
mIoU(ms+flip): 78.59 mIoU(ms+flip): 78.59
Task: Semantic Segmentation Config: configs/gcnet/gcnet_r101-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806-1e38208d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806-1e38208d.pth

9
configs/hrnet/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/HRNet/HRNet-Semantic-Segmentation">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1908.07919">HRNet (CVPR'2019)</a></summary>
```latext ```latext
@inproceedings{SunXLW19, @inproceedings{SunXLW19,
title={Deep High-Resolution Representation Learning for Human Pose Estimation}, title={Deep High-Resolution Representation Learning for Human Pose Estimation},
@ -13,6 +20,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

243
configs/hrnet/hrnet.yml
View File

@ -1,440 +1,449 @@
Collections: Collections:
- Metadata: - Name: hrnet
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20K - ADE20K
- Pascal VOC 2012 + Aug - Pascal VOC 2012 + Aug
- Pascal Context - Pascal Context
- Pascal Context 59 - Pascal Context 59
Name: hrnet Paper:
URL: https://arxiv.org/abs/1908.07919
Title: Deep High-Resolution Representation Learning for Human Pose Estimation
README: configs/hrnet/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218
Version: v0.17.0
Converted From:
Code: https://github.com/HRNet/HRNet-Semantic-Segmentation
Models: Models:
- Config: configs/hrnet/fcn_hr18s_512x1024_40k_cityscapes.py - Name: fcn_hr18s_512x1024_40k_cityscapes
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W18-Small backbone: HRNetV2p-W18-Small
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 42.12
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 42.12
lr schd: 40000
memory (GB): 1.7 memory (GB): 1.7
Name: fcn_hr18s_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 73.86 mIoU: 73.86
mIoU(ms+flip): 75.91 mIoU(ms+flip): 75.91
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr18s_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_40k_cityscapes/fcn_hr18s_512x1024_40k_cityscapes_20200601_014216-93db27d0.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_40k_cityscapes/fcn_hr18s_512x1024_40k_cityscapes_20200601_014216-93db27d0.pth
- Config: configs/hrnet/fcn_hr18_512x1024_40k_cityscapes.py - Name: fcn_hr18_512x1024_40k_cityscapes
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W18 backbone: HRNetV2p-W18
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 77.1
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 77.1
lr schd: 40000
memory (GB): 2.9 memory (GB): 2.9
Name: fcn_hr18_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.19 mIoU: 77.19
mIoU(ms+flip): 78.92 mIoU(ms+flip): 78.92
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr18_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_40k_cityscapes/fcn_hr18_512x1024_40k_cityscapes_20200601_014216-f196fb4e.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_40k_cityscapes/fcn_hr18_512x1024_40k_cityscapes_20200601_014216-f196fb4e.pth
- Config: configs/hrnet/fcn_hr48_512x1024_40k_cityscapes.py - Name: fcn_hr48_512x1024_40k_cityscapes
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W48 backbone: HRNetV2p-W48
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 155.76
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 155.76
lr schd: 40000
memory (GB): 6.2 memory (GB): 6.2
Name: fcn_hr48_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.48 mIoU: 78.48
mIoU(ms+flip): 79.69 mIoU(ms+flip): 79.69
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr48_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_40k_cityscapes/fcn_hr48_512x1024_40k_cityscapes_20200601_014240-a989b146.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_40k_cityscapes/fcn_hr48_512x1024_40k_cityscapes_20200601_014240-a989b146.pth
- Config: configs/hrnet/fcn_hr18s_512x1024_80k_cityscapes.py - Name: fcn_hr18s_512x1024_80k_cityscapes
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W18-Small backbone: HRNetV2p-W18-Small
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: fcn_hr18s_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 75.31 mIoU: 75.31
mIoU(ms+flip): 77.48 mIoU(ms+flip): 77.48
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr18s_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_80k_cityscapes/fcn_hr18s_512x1024_80k_cityscapes_20200601_202700-1462b75d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_80k_cityscapes/fcn_hr18s_512x1024_80k_cityscapes_20200601_202700-1462b75d.pth
- Config: configs/hrnet/fcn_hr18_512x1024_80k_cityscapes.py - Name: fcn_hr18_512x1024_80k_cityscapes
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W18 backbone: HRNetV2p-W18
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: fcn_hr18_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.65 mIoU: 78.65
mIoU(ms+flip): 80.35 mIoU(ms+flip): 80.35
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr18_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_80k_cityscapes/fcn_hr18_512x1024_80k_cityscapes_20200601_223255-4e7b345e.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_80k_cityscapes/fcn_hr18_512x1024_80k_cityscapes_20200601_223255-4e7b345e.pth
- Config: configs/hrnet/fcn_hr48_512x1024_80k_cityscapes.py - Name: fcn_hr48_512x1024_80k_cityscapes
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W48 backbone: HRNetV2p-W48
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: fcn_hr48_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.93 mIoU: 79.93
mIoU(ms+flip): 80.72 mIoU(ms+flip): 80.72
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr48_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_80k_cityscapes/fcn_hr48_512x1024_80k_cityscapes_20200601_202606-58ea95d6.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_80k_cityscapes/fcn_hr48_512x1024_80k_cityscapes_20200601_202606-58ea95d6.pth
- Config: configs/hrnet/fcn_hr18s_512x1024_160k_cityscapes.py - Name: fcn_hr18s_512x1024_160k_cityscapes
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W18-Small backbone: HRNetV2p-W18-Small
crop size: (512,1024) crop size: (512,1024)
lr schd: 160000 lr schd: 160000
Name: fcn_hr18s_512x1024_160k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 76.31 mIoU: 76.31
mIoU(ms+flip): 78.31 mIoU(ms+flip): 78.31
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr18s_512x1024_160k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_160k_cityscapes/fcn_hr18s_512x1024_160k_cityscapes_20200602_190901-4a0797ea.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_160k_cityscapes/fcn_hr18s_512x1024_160k_cityscapes_20200602_190901-4a0797ea.pth
- Config: configs/hrnet/fcn_hr18_512x1024_160k_cityscapes.py - Name: fcn_hr18_512x1024_160k_cityscapes
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W18 backbone: HRNetV2p-W18
crop size: (512,1024) crop size: (512,1024)
lr schd: 160000 lr schd: 160000
Name: fcn_hr18_512x1024_160k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.8 mIoU: 78.8
mIoU(ms+flip): 80.74 mIoU(ms+flip): 80.74
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr18_512x1024_160k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_160k_cityscapes/fcn_hr18_512x1024_160k_cityscapes_20200602_190822-221e4a4f.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_160k_cityscapes/fcn_hr18_512x1024_160k_cityscapes_20200602_190822-221e4a4f.pth
- Config: configs/hrnet/fcn_hr48_512x1024_160k_cityscapes.py - Name: fcn_hr48_512x1024_160k_cityscapes
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W48 backbone: HRNetV2p-W48
crop size: (512,1024) crop size: (512,1024)
lr schd: 160000 lr schd: 160000
Name: fcn_hr48_512x1024_160k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.65 mIoU: 80.65
mIoU(ms+flip): 81.92 mIoU(ms+flip): 81.92
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr48_512x1024_160k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_160k_cityscapes/fcn_hr48_512x1024_160k_cityscapes_20200602_190946-59b7973e.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_160k_cityscapes/fcn_hr48_512x1024_160k_cityscapes_20200602_190946-59b7973e.pth
- Config: configs/hrnet/fcn_hr18s_512x512_80k_ade20k.py - Name: fcn_hr18s_512x512_80k_ade20k
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W18-Small backbone: HRNetV2p-W18-Small
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 25.87
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 25.87
lr schd: 80000
memory (GB): 3.8 memory (GB): 3.8
Name: fcn_hr18s_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 31.38 mIoU: 31.38
mIoU(ms+flip): 32.45 mIoU(ms+flip): 32.45
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr18s_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_ade20k/fcn_hr18s_512x512_80k_ade20k_20200614_144345-77fc814a.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_ade20k/fcn_hr18s_512x512_80k_ade20k_20200614_144345-77fc814a.pth
- Config: configs/hrnet/fcn_hr18_512x512_80k_ade20k.py - Name: fcn_hr18_512x512_80k_ade20k
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W18 backbone: HRNetV2p-W18
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 44.31
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 44.31
lr schd: 80000
memory (GB): 4.9 memory (GB): 4.9
Name: fcn_hr18_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 36.27 mIoU: 36.27
mIoU(ms+flip): 37.28 mIoU(ms+flip): 37.28
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr18_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20210827_114910-6c9382c0.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20210827_114910-6c9382c0.pth
- Config: configs/hrnet/fcn_hr48_512x512_80k_ade20k.py - Name: fcn_hr48_512x512_80k_ade20k
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W48 backbone: HRNetV2p-W48
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 47.1
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 47.1
lr schd: 80000
memory (GB): 8.2 memory (GB): 8.2
Name: fcn_hr48_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 41.9 mIoU: 41.9
mIoU(ms+flip): 43.27 mIoU(ms+flip): 43.27
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr48_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_ade20k/fcn_hr48_512x512_80k_ade20k_20200614_193946-7ba5258d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_ade20k/fcn_hr48_512x512_80k_ade20k_20200614_193946-7ba5258d.pth
- Config: configs/hrnet/fcn_hr18s_512x512_160k_ade20k.py - Name: fcn_hr18s_512x512_160k_ade20k
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W18-Small backbone: HRNetV2p-W18-Small
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: fcn_hr18s_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 33.07 mIoU: 33.07
mIoU(ms+flip): 34.56 mIoU(ms+flip): 34.56
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr18s_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20210829_174739-f1e7c2e7.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20210829_174739-f1e7c2e7.pth
- Config: configs/hrnet/fcn_hr18_512x512_160k_ade20k.py - Name: fcn_hr18_512x512_160k_ade20k
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W18 backbone: HRNetV2p-W18
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: fcn_hr18_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 36.79 mIoU: 36.79
mIoU(ms+flip): 38.58 mIoU(ms+flip): 38.58
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr18_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_160k_ade20k/fcn_hr18_512x512_160k_ade20k_20200614_214426-ca961836.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_160k_ade20k/fcn_hr18_512x512_160k_ade20k_20200614_214426-ca961836.pth
- Config: configs/hrnet/fcn_hr48_512x512_160k_ade20k.py - Name: fcn_hr48_512x512_160k_ade20k
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W48 backbone: HRNetV2p-W48
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: fcn_hr48_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.02 mIoU: 42.02
mIoU(ms+flip): 43.86 mIoU(ms+flip): 43.86
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr48_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_160k_ade20k/fcn_hr48_512x512_160k_ade20k_20200614_214407-a52fc02c.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_160k_ade20k/fcn_hr48_512x512_160k_ade20k_20200614_214407-a52fc02c.pth
- Config: configs/hrnet/fcn_hr18s_512x512_20k_voc12aug.py - Name: fcn_hr18s_512x512_20k_voc12aug
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W18-Small backbone: HRNetV2p-W18-Small
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 23.06
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 23.06
lr schd: 20000
memory (GB): 1.8 memory (GB): 1.8
Name: fcn_hr18s_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 65.5 mIoU: 65.5
mIoU(ms+flip): 68.89 mIoU(ms+flip): 68.89
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr18s_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20210829_174910-0aceadb4.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20210829_174910-0aceadb4.pth
- Config: configs/hrnet/fcn_hr18_512x512_20k_voc12aug.py - Name: fcn_hr18_512x512_20k_voc12aug
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W18 backbone: HRNetV2p-W18
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 42.59
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 42.59
lr schd: 20000
memory (GB): 2.9 memory (GB): 2.9
Name: fcn_hr18_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 72.3 mIoU: 72.3
mIoU(ms+flip): 74.71 mIoU(ms+flip): 74.71
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr18_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_20k_voc12aug/fcn_hr18_512x512_20k_voc12aug_20200617_224503-488d45f7.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_20k_voc12aug/fcn_hr18_512x512_20k_voc12aug_20200617_224503-488d45f7.pth
- Config: configs/hrnet/fcn_hr48_512x512_20k_voc12aug.py - Name: fcn_hr48_512x512_20k_voc12aug
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W48 backbone: HRNetV2p-W48
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 45.35
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 45.35
lr schd: 20000
memory (GB): 6.2 memory (GB): 6.2
Name: fcn_hr48_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 75.87 mIoU: 75.87
mIoU(ms+flip): 78.58 mIoU(ms+flip): 78.58
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr48_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_20k_voc12aug/fcn_hr48_512x512_20k_voc12aug_20200617_224419-89de05cd.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_20k_voc12aug/fcn_hr48_512x512_20k_voc12aug_20200617_224419-89de05cd.pth
- Config: configs/hrnet/fcn_hr18s_512x512_40k_voc12aug.py - Name: fcn_hr18s_512x512_40k_voc12aug
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W18-Small backbone: HRNetV2p-W18-Small
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: fcn_hr18s_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 66.61 mIoU: 66.61
mIoU(ms+flip): 70.0 mIoU(ms+flip): 70.0
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr18s_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_40k_voc12aug/fcn_hr18s_512x512_40k_voc12aug_20200614_000648-4f8d6e7f.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_40k_voc12aug/fcn_hr18s_512x512_40k_voc12aug_20200614_000648-4f8d6e7f.pth
- Config: configs/hrnet/fcn_hr18_512x512_40k_voc12aug.py - Name: fcn_hr18_512x512_40k_voc12aug
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W18 backbone: HRNetV2p-W18
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: fcn_hr18_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 72.9 mIoU: 72.9
mIoU(ms+flip): 75.59 mIoU(ms+flip): 75.59
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr18_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_40k_voc12aug/fcn_hr18_512x512_40k_voc12aug_20200613_224401-1b4b76cd.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_40k_voc12aug/fcn_hr18_512x512_40k_voc12aug_20200613_224401-1b4b76cd.pth
- Config: configs/hrnet/fcn_hr48_512x512_40k_voc12aug.py - Name: fcn_hr48_512x512_40k_voc12aug
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W48 backbone: HRNetV2p-W48
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: fcn_hr48_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 76.24 mIoU: 76.24
mIoU(ms+flip): 78.49 mIoU(ms+flip): 78.49
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr48_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_40k_voc12aug/fcn_hr48_512x512_40k_voc12aug_20200613_222111-1b0f18bc.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_40k_voc12aug/fcn_hr48_512x512_40k_voc12aug_20200613_222111-1b0f18bc.pth
- Config: configs/hrnet/fcn_hr48_480x480_40k_pascal_context.py - Name: fcn_hr48_480x480_40k_pascal_context
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W48 backbone: HRNetV2p-W48
crop size: (480,480) crop size: (480,480)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 112.87
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (480,480) resolution: (480,480)
value: 112.87
lr schd: 40000
memory (GB): 6.1 memory (GB): 6.1
Name: fcn_hr48_480x480_40k_pascal_context
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal Context Dataset: Pascal Context
Metrics: Metrics:
mIoU: 45.14 mIoU: 45.14
mIoU(ms+flip): 47.42 mIoU(ms+flip): 47.42
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr48_480x480_40k_pascal_context.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context/fcn_hr48_480x480_40k_pascal_context_20200911_164852-667d00b0.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context/fcn_hr48_480x480_40k_pascal_context_20200911_164852-667d00b0.pth
- Config: configs/hrnet/fcn_hr48_480x480_80k_pascal_context.py - Name: fcn_hr48_480x480_80k_pascal_context
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W48 backbone: HRNetV2p-W48
crop size: (480,480) crop size: (480,480)
lr schd: 80000 lr schd: 80000
Name: fcn_hr48_480x480_80k_pascal_context
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal Context Dataset: Pascal Context
Metrics: Metrics:
mIoU: 45.84 mIoU: 45.84
mIoU(ms+flip): 47.84 mIoU(ms+flip): 47.84
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr48_480x480_80k_pascal_context.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context/fcn_hr48_480x480_80k_pascal_context_20200911_155322-847a6711.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context/fcn_hr48_480x480_80k_pascal_context_20200911_155322-847a6711.pth
- Config: configs/hrnet/fcn_hr48_480x480_40k_pascal_context_59.py - Name: fcn_hr48_480x480_40k_pascal_context_59
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W48 backbone: HRNetV2p-W48
crop size: (480,480) crop size: (480,480)
lr schd: 40000 lr schd: 40000
Name: fcn_hr48_480x480_40k_pascal_context_59
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal Context 59 Dataset: Pascal Context 59
Metrics: Metrics:
mIoU: 50.33 mIoU: 50.33
mIoU(ms+flip): 52.83 mIoU(ms+flip): 52.83
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr48_480x480_40k_pascal_context_59.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59_20210410_122738-b808b8b2.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59_20210410_122738-b808b8b2.pth
- Config: configs/hrnet/fcn_hr48_480x480_80k_pascal_context_59.py - Name: fcn_hr48_480x480_80k_pascal_context_59
In Collection: hrnet In Collection: hrnet
Metadata: Metadata:
backbone: HRNetV2p-W48 backbone: HRNetV2p-W48
crop size: (480,480) crop size: (480,480)
lr schd: 80000 lr schd: 80000
Name: fcn_hr48_480x480_80k_pascal_context_59
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal Context 59 Dataset: Pascal Context 59
Metrics: Metrics:
mIoU: 51.12 mIoU: 51.12
mIoU(ms+flip): 53.56 mIoU(ms+flip): 53.56
Task: Semantic Segmentation Config: configs/hrnet/fcn_hr48_480x480_80k_pascal_context_59.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59_20210411_003240-3ae7081e.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59_20210411_003240-3ae7081e.pth

9
configs/isanet/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/openseg-group/openseg.pytorch">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1907.12273">ISANet (ArXiv'2019/IJCV'2021)</a></summary>
``` ```
@article{huang2019isa, @article{huang2019isa,
title={Interlaced Sparse Self-Attention for Semantic Segmentation}, title={Interlaced Sparse Self-Attention for Semantic Segmentation},
@ -23,6 +30,8 @@ The technical report above is also presented at:
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

237
configs/isanet/isanet.yml
View File

@ -1,360 +1,369 @@
Collections: Collections:
- Metadata: - Name: isanet
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20K - ADE20K
- Pascal VOC 2012 + Aug - Pascal VOC 2012 + Aug
Name: isanet Paper:
URL: https://arxiv.org/abs/1907.12273
Title: Interlaced Sparse Self-Attention for Semantic Segmentation
README: configs/isanet/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/decode_heads/isa_head.py#L58
Version: v0.18.0
Converted From:
Code: https://github.com/openseg-group/openseg.pytorch
Models: Models:
- Config: configs/isanet/isanet_r50-d8_512x1024_40k_cityscapes.py - Name: isanet_r50-d8_512x1024_40k_cityscapes
In Collection: isanet In Collection: isanet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 343.64
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 343.64
lr schd: 40000
memory (GB): 5.869 memory (GB): 5.869
Name: isanet_r50-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.49 mIoU: 78.49
mIoU(ms+flip): 79.44 mIoU(ms+flip): 79.44
Task: Semantic Segmentation Config: configs/isanet/isanet_r50-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_40k_cityscapes/isanet_r50-d8_512x1024_40k_cityscapes_20210901_054739-981bd763.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_40k_cityscapes/isanet_r50-d8_512x1024_40k_cityscapes_20210901_054739-981bd763.pth
- Config: configs/isanet/isanet_r50-d8_512x1024_80k_cityscapes.py - Name: isanet_r50-d8_512x1024_80k_cityscapes
In Collection: isanet In Collection: isanet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 343.64
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 343.64
lr schd: 80000
memory (GB): 5.869 memory (GB): 5.869
Name: isanet_r50-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.68 mIoU: 78.68
mIoU(ms+flip): 80.25 mIoU(ms+flip): 80.25
Task: Semantic Segmentation Config: configs/isanet/isanet_r50-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_80k_cityscapes/isanet_r50-d8_512x1024_80k_cityscapes_20210901_074202-89384497.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x1024_80k_cityscapes/isanet_r50-d8_512x1024_80k_cityscapes_20210901_074202-89384497.pth
- Config: configs/isanet/isanet_r50-d8_769x769_40k_cityscapes.py - Name: isanet_r50-d8_769x769_40k_cityscapes
In Collection: isanet In Collection: isanet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 649.35
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 649.35
lr schd: 40000
memory (GB): 6.759 memory (GB): 6.759
Name: isanet_r50-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.7 mIoU: 78.7
mIoU(ms+flip): 80.28 mIoU(ms+flip): 80.28
Task: Semantic Segmentation Config: configs/isanet/isanet_r50-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_40k_cityscapes/isanet_r50-d8_769x769_40k_cityscapes_20210903_050200-4ae7e65b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_40k_cityscapes/isanet_r50-d8_769x769_40k_cityscapes_20210903_050200-4ae7e65b.pth
- Config: configs/isanet/isanet_r50-d8_769x769_80k_cityscapes.py - Name: isanet_r50-d8_769x769_80k_cityscapes
In Collection: isanet In Collection: isanet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 649.35
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 649.35
lr schd: 80000
memory (GB): 6.759 memory (GB): 6.759
Name: isanet_r50-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.29 mIoU: 79.29
mIoU(ms+flip): 80.53 mIoU(ms+flip): 80.53
Task: Semantic Segmentation Config: configs/isanet/isanet_r50-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_80k_cityscapes/isanet_r50-d8_769x769_80k_cityscapes_20210903_101126-99b54519.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_769x769_80k_cityscapes/isanet_r50-d8_769x769_80k_cityscapes_20210903_101126-99b54519.pth
- Config: configs/isanet/isanet_r101-d8_512x1024_40k_cityscapes.py - Name: isanet_r101-d8_512x1024_40k_cityscapes
In Collection: isanet In Collection: isanet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 425.53
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 425.53
lr schd: 40000
memory (GB): 9.425 memory (GB): 9.425
Name: isanet_r101-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.58 mIoU: 79.58
mIoU(ms+flip): 81.05 mIoU(ms+flip): 81.05
Task: Semantic Segmentation Config: configs/isanet/isanet_r101-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_40k_cityscapes/isanet_r101-d8_512x1024_40k_cityscapes_20210901_145553-293e6bd6.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_40k_cityscapes/isanet_r101-d8_512x1024_40k_cityscapes_20210901_145553-293e6bd6.pth
- Config: configs/isanet/isanet_r101-d8_512x1024_80k_cityscapes.py - Name: isanet_r101-d8_512x1024_80k_cityscapes
In Collection: isanet In Collection: isanet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 425.53
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 425.53
lr schd: 80000
memory (GB): 9.425 memory (GB): 9.425
Name: isanet_r101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.32 mIoU: 80.32
mIoU(ms+flip): 81.58 mIoU(ms+flip): 81.58
Task: Semantic Segmentation Config: configs/isanet/isanet_r101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_80k_cityscapes/isanet_r101-d8_512x1024_80k_cityscapes_20210901_145243-5b99c9b2.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x1024_80k_cityscapes/isanet_r101-d8_512x1024_80k_cityscapes_20210901_145243-5b99c9b2.pth
- Config: configs/isanet/isanet_r101-d8_769x769_40k_cityscapes.py - Name: isanet_r101-d8_769x769_40k_cityscapes
In Collection: isanet In Collection: isanet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 1086.96
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 1086.96
lr schd: 40000
memory (GB): 10.815 memory (GB): 10.815
Name: isanet_r101-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.68 mIoU: 79.68
mIoU(ms+flip): 80.95 mIoU(ms+flip): 80.95
Task: Semantic Segmentation Config: configs/isanet/isanet_r101-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_40k_cityscapes/isanet_r101-d8_769x769_40k_cityscapes_20210903_111320-509e7224.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_40k_cityscapes/isanet_r101-d8_769x769_40k_cityscapes_20210903_111320-509e7224.pth
- Config: configs/isanet/isanet_r101-d8_769x769_80k_cityscapes.py - Name: isanet_r101-d8_769x769_80k_cityscapes
In Collection: isanet In Collection: isanet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 1086.96
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 1086.96
lr schd: 80000
memory (GB): 10.815 memory (GB): 10.815
Name: isanet_r101-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.61 mIoU: 80.61
mIoU(ms+flip): 81.59 mIoU(ms+flip): 81.59
Task: Semantic Segmentation Config: configs/isanet/isanet_r101-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_80k_cityscapes/isanet_r101-d8_769x769_80k_cityscapes_20210903_111319-24f71dfa.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_769x769_80k_cityscapes/isanet_r101-d8_769x769_80k_cityscapes_20210903_111319-24f71dfa.pth
- Config: configs/isanet/isanet_r50-d8_512x512_80k_ade20k.py - Name: isanet_r50-d8_512x512_80k_ade20k
In Collection: isanet In Collection: isanet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 44.35
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 44.35
lr schd: 80000
memory (GB): 9.0 memory (GB): 9.0
Name: isanet_r50-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 41.12 mIoU: 41.12
mIoU(ms+flip): 42.35 mIoU(ms+flip): 42.35
Task: Semantic Segmentation Config: configs/isanet/isanet_r50-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_80k_ade20k/isanet_r50-d8_512x512_80k_ade20k_20210903_124557-6ed83a0c.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_80k_ade20k/isanet_r50-d8_512x512_80k_ade20k_20210903_124557-6ed83a0c.pth
- Config: configs/isanet/isanet_r50-d8_512x512_160k_ade20k.py - Name: isanet_r50-d8_512x512_160k_ade20k
In Collection: isanet In Collection: isanet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 44.35
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 44.35
lr schd: 160000
memory (GB): 9.0 memory (GB): 9.0
Name: isanet_r50-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.59 mIoU: 42.59
mIoU(ms+flip): 43.07 mIoU(ms+flip): 43.07
Task: Semantic Segmentation Config: configs/isanet/isanet_r50-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_160k_ade20k/isanet_r50-d8_512x512_160k_ade20k_20210903_104850-f752d0a3.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_160k_ade20k/isanet_r50-d8_512x512_160k_ade20k_20210903_104850-f752d0a3.pth
- Config: configs/isanet/isanet_r101-d8_512x512_80k_ade20k.py - Name: isanet_r101-d8_512x512_80k_ade20k
In Collection: isanet In Collection: isanet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 94.7
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 94.7
lr schd: 80000
memory (GB): 12.562 memory (GB): 12.562
Name: isanet_r101-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 43.51 mIoU: 43.51
mIoU(ms+flip): 44.38 mIoU(ms+flip): 44.38
Task: Semantic Segmentation Config: configs/isanet/isanet_r101-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_80k_ade20k/isanet_r101-d8_512x512_80k_ade20k_20210903_162056-68b235c2.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_80k_ade20k/isanet_r101-d8_512x512_80k_ade20k_20210903_162056-68b235c2.pth
- Config: configs/isanet/isanet_r101-d8_512x512_160k_ade20k.py - Name: isanet_r101-d8_512x512_160k_ade20k
In Collection: isanet In Collection: isanet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 94.7
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 94.7
lr schd: 160000
memory (GB): 12.562 memory (GB): 12.562
Name: isanet_r101-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 43.8 mIoU: 43.8
mIoU(ms+flip): 45.4 mIoU(ms+flip): 45.4
Task: Semantic Segmentation Config: configs/isanet/isanet_r101-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_160k_ade20k/isanet_r101-d8_512x512_160k_ade20k_20210903_211431-a7879dcd.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_160k_ade20k/isanet_r101-d8_512x512_160k_ade20k_20210903_211431-a7879dcd.pth
- Config: configs/isanet/isanet_r50-d8_512x512_20k_voc12aug.py - Name: isanet_r50-d8_512x512_20k_voc12aug
In Collection: isanet In Collection: isanet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 43.33
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 43.33
lr schd: 20000
memory (GB): 5.9 memory (GB): 5.9
Name: isanet_r50-d8_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 76.78 mIoU: 76.78
mIoU(ms+flip): 77.79 mIoU(ms+flip): 77.79
Task: Semantic Segmentation Config: configs/isanet/isanet_r50-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_20k_voc12aug/isanet_r50-d8_512x512_20k_voc12aug_20210901_164838-79d59b80.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_20k_voc12aug/isanet_r50-d8_512x512_20k_voc12aug_20210901_164838-79d59b80.pth
- Config: configs/isanet/isanet_r50-d8_512x512_40k_voc12aug.py - Name: isanet_r50-d8_512x512_40k_voc12aug
In Collection: isanet In Collection: isanet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 43.33
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 43.33
lr schd: 40000
memory (GB): 5.9 memory (GB): 5.9
Name: isanet_r50-d8_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 76.2 mIoU: 76.2
mIoU(ms+flip): 77.22 mIoU(ms+flip): 77.22
Task: Semantic Segmentation Config: configs/isanet/isanet_r50-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_40k_voc12aug/isanet_r50-d8_512x512_40k_voc12aug_20210901_151349-7d08a54e.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r50-d8_512x512_40k_voc12aug/isanet_r50-d8_512x512_40k_voc12aug_20210901_151349-7d08a54e.pth
- Config: configs/isanet/isanet_r101-d8_512x512_20k_voc12aug.py - Name: isanet_r101-d8_512x512_20k_voc12aug
In Collection: isanet In Collection: isanet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 134.77
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 134.77
lr schd: 20000
memory (GB): 9.465 memory (GB): 9.465
Name: isanet_r101-d8_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 78.46 mIoU: 78.46
mIoU(ms+flip): 79.16 mIoU(ms+flip): 79.16
Task: Semantic Segmentation Config: configs/isanet/isanet_r101-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_20k_voc12aug/isanet_r101-d8_512x512_20k_voc12aug_20210901_115805-3ccbf355.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_20k_voc12aug/isanet_r101-d8_512x512_20k_voc12aug_20210901_115805-3ccbf355.pth
- Config: configs/isanet/isanet_r101-d8_512x512_40k_voc12aug.py - Name: isanet_r101-d8_512x512_40k_voc12aug
In Collection: isanet In Collection: isanet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 134.77
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 134.77
lr schd: 40000
memory (GB): 9.465 memory (GB): 9.465
Name: isanet_r101-d8_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 78.12 mIoU: 78.12
mIoU(ms+flip): 79.04 mIoU(ms+flip): 79.04
Task: Semantic Segmentation Config: configs/isanet/isanet_r101-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_40k_voc12aug/isanet_r101-d8_512x512_40k_voc12aug_20210901_145814-bc71233b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/isanet/isanet_r101-d8_512x512_40k_voc12aug/isanet_r101-d8_512x512_40k_voc12aug_20210901_145814-bc71233b.pth

9
configs/mobilenet_v2/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/tensorflow/models/tree/master/research/deeplab">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mobilenet_v2.py#L14">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1801.04381">MobileNetV2 (CVPR'2018)</a></summary>
```latex ```latex
@inproceedings{sandler2018mobilenetv2, @inproceedings{sandler2018mobilenetv2,
title={Mobilenetv2: Inverted residuals and linear bottlenecks}, title={Mobilenetv2: Inverted residuals and linear bottlenecks},
@ -14,6 +21,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

125
configs/mobilenet_v2/mobilenet_v2.yml
View File

@ -1,175 +1,184 @@
Collections: Collections:
- Metadata: - Name: mobilenet_v2
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20k - ADE20k
Name: mobilenet_v2 Paper:
URL: https://arxiv.org/abs/1801.04381
Title: 'MobileNetV2: Inverted Residuals and Linear Bottlenecks'
README: configs/mobilenet_v2/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mobilenet_v2.py#L14
Version: v0.17.0
Converted From:
Code: https://github.com/tensorflow/models/tree/master/research/deeplab
Models: Models:
- Config: configs/mobilenet_v2/fcn_m-v2-d8_512x1024_80k_cityscapes.py - Name: fcn_m-v2-d8_512x1024_80k_cityscapes
In Collection: mobilenet_v2 In Collection: mobilenet_v2
Metadata: Metadata:
backbone: M-V2-D8 backbone: M-V2-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 70.42
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 70.42
lr schd: 80000
memory (GB): 3.4 memory (GB): 3.4
Name: fcn_m-v2-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 61.54 mIoU: 61.54
Task: Semantic Segmentation Config: configs/mobilenet_v2/fcn_m-v2-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/fcn_m-v2-d8_512x1024_80k_cityscapes/fcn_m-v2-d8_512x1024_80k_cityscapes_20200825_124817-d24c28c1.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/fcn_m-v2-d8_512x1024_80k_cityscapes/fcn_m-v2-d8_512x1024_80k_cityscapes_20200825_124817-d24c28c1.pth
- Config: configs/mobilenet_v2/pspnet_m-v2-d8_512x1024_80k_cityscapes.py - Name: pspnet_m-v2-d8_512x1024_80k_cityscapes
In Collection: mobilenet_v2 In Collection: mobilenet_v2
Metadata: Metadata:
backbone: M-V2-D8 backbone: M-V2-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 89.29
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 89.29
lr schd: 80000
memory (GB): 3.6 memory (GB): 3.6
Name: pspnet_m-v2-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 70.23 mIoU: 70.23
Task: Semantic Segmentation Config: configs/mobilenet_v2/pspnet_m-v2-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x1024_80k_cityscapes/pspnet_m-v2-d8_512x1024_80k_cityscapes_20200825_124817-19e81d51.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x1024_80k_cityscapes/pspnet_m-v2-d8_512x1024_80k_cityscapes_20200825_124817-19e81d51.pth
- Config: configs/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes.py - Name: deeplabv3_m-v2-d8_512x1024_80k_cityscapes
In Collection: mobilenet_v2 In Collection: mobilenet_v2
Metadata: Metadata:
backbone: M-V2-D8 backbone: M-V2-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 119.05
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 119.05
lr schd: 80000
memory (GB): 3.9 memory (GB): 3.9
Name: deeplabv3_m-v2-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 73.84 mIoU: 73.84
Task: Semantic Segmentation Config: configs/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes/deeplabv3_m-v2-d8_512x1024_80k_cityscapes_20200825_124836-bef03590.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes/deeplabv3_m-v2-d8_512x1024_80k_cityscapes_20200825_124836-bef03590.pth
- Config: configs/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes.py - Name: deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes
In Collection: mobilenet_v2 In Collection: mobilenet_v2
Metadata: Metadata:
backbone: M-V2-D8 backbone: M-V2-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 119.05
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 119.05
lr schd: 80000
memory (GB): 5.1 memory (GB): 5.1
Name: deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 75.2 mIoU: 75.2
Task: Semantic Segmentation Config: configs/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes_20200825_124836-d256dd4b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes_20200825_124836-d256dd4b.pth
- Config: configs/mobilenet_v2/fcn_m-v2-d8_512x512_160k_ade20k.py - Name: fcn_m-v2-d8_512x512_160k_ade20k
In Collection: mobilenet_v2 In Collection: mobilenet_v2
Metadata: Metadata:
backbone: M-V2-D8 backbone: M-V2-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 15.53
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 15.53
lr schd: 160000
memory (GB): 6.5 memory (GB): 6.5
Name: fcn_m-v2-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20k Dataset: ADE20k
Metrics: Metrics:
mIoU: 19.71 mIoU: 19.71
Task: Semantic Segmentation Config: configs/mobilenet_v2/fcn_m-v2-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/fcn_m-v2-d8_512x512_160k_ade20k/fcn_m-v2-d8_512x512_160k_ade20k_20200825_214953-c40e1095.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/fcn_m-v2-d8_512x512_160k_ade20k/fcn_m-v2-d8_512x512_160k_ade20k_20200825_214953-c40e1095.pth
- Config: configs/mobilenet_v2/pspnet_m-v2-d8_512x512_160k_ade20k.py - Name: pspnet_m-v2-d8_512x512_160k_ade20k
In Collection: mobilenet_v2 In Collection: mobilenet_v2
Metadata: Metadata:
backbone: M-V2-D8 backbone: M-V2-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 17.33
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 17.33
lr schd: 160000
memory (GB): 6.5 memory (GB): 6.5
Name: pspnet_m-v2-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20k Dataset: ADE20k
Metrics: Metrics:
mIoU: 29.68 mIoU: 29.68
Task: Semantic Segmentation Config: configs/mobilenet_v2/pspnet_m-v2-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x512_160k_ade20k/pspnet_m-v2-d8_512x512_160k_ade20k_20200825_214953-f5942f7a.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/pspnet_m-v2-d8_512x512_160k_ade20k/pspnet_m-v2-d8_512x512_160k_ade20k_20200825_214953-f5942f7a.pth
- Config: configs/mobilenet_v2/deeplabv3_m-v2-d8_512x512_160k_ade20k.py - Name: deeplabv3_m-v2-d8_512x512_160k_ade20k
In Collection: mobilenet_v2 In Collection: mobilenet_v2
Metadata: Metadata:
backbone: M-V2-D8 backbone: M-V2-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 25.06
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 25.06
lr schd: 160000
memory (GB): 6.8 memory (GB): 6.8
Name: deeplabv3_m-v2-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20k Dataset: ADE20k
Metrics: Metrics:
mIoU: 34.08 mIoU: 34.08
Task: Semantic Segmentation Config: configs/mobilenet_v2/deeplabv3_m-v2-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x512_160k_ade20k/deeplabv3_m-v2-d8_512x512_160k_ade20k_20200825_223255-63986343.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x512_160k_ade20k/deeplabv3_m-v2-d8_512x512_160k_ade20k_20200825_223255-63986343.pth
- Config: configs/mobilenet_v2/deeplabv3plus_m-v2-d8_512x512_160k_ade20k.py - Name: deeplabv3plus_m-v2-d8_512x512_160k_ade20k
In Collection: mobilenet_v2 In Collection: mobilenet_v2
Metadata: Metadata:
backbone: M-V2-D8 backbone: M-V2-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 23.2
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 23.2
lr schd: 160000
memory (GB): 8.2 memory (GB): 8.2
Name: deeplabv3plus_m-v2-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20k Dataset: ADE20k
Metrics: Metrics:
mIoU: 34.02 mIoU: 34.02
Task: Semantic Segmentation Config: configs/mobilenet_v2/deeplabv3plus_m-v2-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x512_160k_ade20k/deeplabv3plus_m-v2-d8_512x512_160k_ade20k_20200825_223255-465a01d4.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x512_160k_ade20k/deeplabv3plus_m-v2-d8_512x512_160k_ade20k_20200825_223255-465a01d4.pth

9
configs/mobilenet_v3/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/tensorflow/models/tree/master/research/deeplab">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mobilenet_v3.py#L15">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1801.04381">MobileNetV3 (ICCV'2019)</a></summary>
```latex ```latex
@inproceedings{Howard_2019_ICCV, @inproceedings{Howard_2019_ICCV,
title={Searching for MobileNetV3}, title={Searching for MobileNetV3},
@ -16,6 +23,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

69
configs/mobilenet_v3/mobilenet_v3.yml
View File

@ -1,94 +1,103 @@
Collections: Collections:
- Metadata: - Name: mobilenet_v3
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
Name: mobilenet_v3 Paper:
URL: https://arxiv.org/abs/1801.04381
Title: Searching for MobileNetV3
README: configs/mobilenet_v3/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mobilenet_v3.py#L15
Version: v0.17.0
Converted From:
Code: https://github.com/tensorflow/models/tree/master/research/deeplab
Models: Models:
- Config: configs/mobilenet_v3/lraspp_m-v3-d8_512x1024_320k_cityscapes.py - Name: lraspp_m-v3-d8_512x1024_320k_cityscapes
In Collection: mobilenet_v3 In Collection: mobilenet_v3
Metadata: Metadata:
backbone: M-V3-D8 backbone: M-V3-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 320000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 65.7
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 65.7
lr schd: 320000
memory (GB): 8.9 memory (GB): 8.9
Name: lraspp_m-v3-d8_512x1024_320k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 69.54 mIoU: 69.54
mIoU(ms+flip): 70.89 mIoU(ms+flip): 70.89
Task: Semantic Segmentation Config: configs/mobilenet_v3/lraspp_m-v3-d8_512x1024_320k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_512x1024_320k_cityscapes/lraspp_m-v3-d8_512x1024_320k_cityscapes_20201224_220337-cfe8fb07.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_512x1024_320k_cityscapes/lraspp_m-v3-d8_512x1024_320k_cityscapes_20201224_220337-cfe8fb07.pth
- Config: configs/mobilenet_v3/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes.py - Name: lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes
In Collection: mobilenet_v3 In Collection: mobilenet_v3
Metadata: Metadata:
backbone: M-V3-D8 (scratch) backbone: M-V3-D8 (scratch)
crop size: (512,1024) crop size: (512,1024)
lr schd: 320000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 67.7
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 67.7
lr schd: 320000
memory (GB): 8.9 memory (GB): 8.9
Name: lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 67.87 mIoU: 67.87
mIoU(ms+flip): 69.78 mIoU(ms+flip): 69.78
Task: Semantic Segmentation Config: configs/mobilenet_v3/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes_20201224_220337-9f29cd72.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes_20201224_220337-9f29cd72.pth
- Config: configs/mobilenet_v3/lraspp_m-v3s-d8_512x1024_320k_cityscapes.py - Name: lraspp_m-v3s-d8_512x1024_320k_cityscapes
In Collection: mobilenet_v3 In Collection: mobilenet_v3
Metadata: Metadata:
backbone: M-V3s-D8 backbone: M-V3s-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 320000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 42.3
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 42.3
lr schd: 320000
memory (GB): 5.3 memory (GB): 5.3
Name: lraspp_m-v3s-d8_512x1024_320k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 64.11 mIoU: 64.11
mIoU(ms+flip): 66.42 mIoU(ms+flip): 66.42
Task: Semantic Segmentation Config: configs/mobilenet_v3/lraspp_m-v3s-d8_512x1024_320k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_512x1024_320k_cityscapes/lraspp_m-v3s-d8_512x1024_320k_cityscapes_20201224_223935-61565b34.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_512x1024_320k_cityscapes/lraspp_m-v3s-d8_512x1024_320k_cityscapes_20201224_223935-61565b34.pth
- Config: configs/mobilenet_v3/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes.py - Name: lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes
In Collection: mobilenet_v3 In Collection: mobilenet_v3
Metadata: Metadata:
backbone: M-V3s-D8 (scratch) backbone: M-V3s-D8 (scratch)
crop size: (512,1024) crop size: (512,1024)
lr schd: 320000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 40.82
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 40.82
lr schd: 320000
memory (GB): 5.3 memory (GB): 5.3
Name: lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 62.74 mIoU: 62.74
mIoU(ms+flip): 65.01 mIoU(ms+flip): 65.01
Task: Semantic Segmentation Config: configs/mobilenet_v3/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes_20201224_223935-03daeabb.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v3/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes/lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes_20201224_223935-03daeabb.pth

9
configs/nonlocal_net/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/facebookresearch/video-nonlocal-net">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1711.07971">NonLocal Net (CVPR'2018)</a></summary>
```latex ```latex
@inproceedings{wang2018non, @inproceedings{wang2018non,
title={Non-local neural networks}, title={Non-local neural networks},
@ -14,6 +21,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

173
configs/nonlocal_net/nonlocal_net.yml
View File

@ -1,292 +1,301 @@
Collections: Collections:
- Metadata: - Name: nonlocal_net
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20K - ADE20K
- Pascal VOC 2012 + Aug - Pascal VOC 2012 + Aug
Name: nonlocal_net Paper:
URL: https://arxiv.org/abs/1711.07971
Title: Non-local Neural Networks
README: configs/nonlocal_net/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/nl_head.py#L10
Version: v0.17.0
Converted From:
Code: https://github.com/facebookresearch/video-nonlocal-net
Models: Models:
- Config: configs/nonlocal_net/nonlocal_r50-d8_512x1024_40k_cityscapes.py - Name: nonlocal_r50-d8_512x1024_40k_cityscapes
In Collection: nonlocal_net In Collection: nonlocal_net
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 367.65
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 367.65
lr schd: 40000
memory (GB): 7.4 memory (GB): 7.4
Name: nonlocal_r50-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.24 mIoU: 78.24
Task: Semantic Segmentation Config: configs/nonlocal_net/nonlocal_r50-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_40k_cityscapes/nonlocal_r50-d8_512x1024_40k_cityscapes_20200605_210748-c75e81e3.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_40k_cityscapes/nonlocal_r50-d8_512x1024_40k_cityscapes_20200605_210748-c75e81e3.pth
- Config: configs/nonlocal_net/nonlocal_r101-d8_512x1024_40k_cityscapes.py - Name: nonlocal_r101-d8_512x1024_40k_cityscapes
In Collection: nonlocal_net In Collection: nonlocal_net
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 512.82
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 512.82
lr schd: 40000
memory (GB): 10.9 memory (GB): 10.9
Name: nonlocal_r101-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.66 mIoU: 78.66
Task: Semantic Segmentation Config: configs/nonlocal_net/nonlocal_r101-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_40k_cityscapes/nonlocal_r101-d8_512x1024_40k_cityscapes_20200605_210748-d63729fa.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_40k_cityscapes/nonlocal_r101-d8_512x1024_40k_cityscapes_20200605_210748-d63729fa.pth
- Config: configs/nonlocal_net/nonlocal_r50-d8_769x769_40k_cityscapes.py - Name: nonlocal_r50-d8_769x769_40k_cityscapes
In Collection: nonlocal_net In Collection: nonlocal_net
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 657.89
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 657.89
lr schd: 40000
memory (GB): 8.9 memory (GB): 8.9
Name: nonlocal_r50-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.33 mIoU: 78.33
mIoU(ms+flip): 79.92 mIoU(ms+flip): 79.92
Task: Semantic Segmentation Config: configs/nonlocal_net/nonlocal_r50-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_40k_cityscapes/nonlocal_r50-d8_769x769_40k_cityscapes_20200530_045243-82ef6749.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_40k_cityscapes/nonlocal_r50-d8_769x769_40k_cityscapes_20200530_045243-82ef6749.pth
- Config: configs/nonlocal_net/nonlocal_r101-d8_769x769_40k_cityscapes.py - Name: nonlocal_r101-d8_769x769_40k_cityscapes
In Collection: nonlocal_net In Collection: nonlocal_net
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 952.38
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 952.38
lr schd: 40000
memory (GB): 12.8 memory (GB): 12.8
Name: nonlocal_r101-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.57 mIoU: 78.57
mIoU(ms+flip): 80.29 mIoU(ms+flip): 80.29
Task: Semantic Segmentation Config: configs/nonlocal_net/nonlocal_r101-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_40k_cityscapes/nonlocal_r101-d8_769x769_40k_cityscapes_20200530_045348-8fe9a9dc.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_40k_cityscapes/nonlocal_r101-d8_769x769_40k_cityscapes_20200530_045348-8fe9a9dc.pth
- Config: configs/nonlocal_net/nonlocal_r50-d8_512x1024_80k_cityscapes.py - Name: nonlocal_r50-d8_512x1024_80k_cityscapes
In Collection: nonlocal_net In Collection: nonlocal_net
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: nonlocal_r50-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.01 mIoU: 78.01
Task: Semantic Segmentation Config: configs/nonlocal_net/nonlocal_r50-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_80k_cityscapes/nonlocal_r50-d8_512x1024_80k_cityscapes_20200607_193518-d6839fae.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x1024_80k_cityscapes/nonlocal_r50-d8_512x1024_80k_cityscapes_20200607_193518-d6839fae.pth
- Config: configs/nonlocal_net/nonlocal_r101-d8_512x1024_80k_cityscapes.py - Name: nonlocal_r101-d8_512x1024_80k_cityscapes
In Collection: nonlocal_net In Collection: nonlocal_net
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: nonlocal_r101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.93 mIoU: 78.93
Task: Semantic Segmentation Config: configs/nonlocal_net/nonlocal_r101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_80k_cityscapes/nonlocal_r101-d8_512x1024_80k_cityscapes_20200607_183411-32700183.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x1024_80k_cityscapes/nonlocal_r101-d8_512x1024_80k_cityscapes_20200607_183411-32700183.pth
- Config: configs/nonlocal_net/nonlocal_r50-d8_769x769_80k_cityscapes.py - Name: nonlocal_r50-d8_769x769_80k_cityscapes
In Collection: nonlocal_net In Collection: nonlocal_net
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: nonlocal_r50-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.05 mIoU: 79.05
mIoU(ms+flip): 80.68 mIoU(ms+flip): 80.68
Task: Semantic Segmentation Config: configs/nonlocal_net/nonlocal_r50-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_80k_cityscapes/nonlocal_r50-d8_769x769_80k_cityscapes_20200607_193506-1f9792f6.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_769x769_80k_cityscapes/nonlocal_r50-d8_769x769_80k_cityscapes_20200607_193506-1f9792f6.pth
- Config: configs/nonlocal_net/nonlocal_r101-d8_769x769_80k_cityscapes.py - Name: nonlocal_r101-d8_769x769_80k_cityscapes
In Collection: nonlocal_net In Collection: nonlocal_net
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: nonlocal_r101-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.4 mIoU: 79.4
mIoU(ms+flip): 80.85 mIoU(ms+flip): 80.85
Task: Semantic Segmentation Config: configs/nonlocal_net/nonlocal_r101-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_80k_cityscapes/nonlocal_r101-d8_769x769_80k_cityscapes_20200607_183428-0e1fa4f9.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_769x769_80k_cityscapes/nonlocal_r101-d8_769x769_80k_cityscapes_20200607_183428-0e1fa4f9.pth
- Config: configs/nonlocal_net/nonlocal_r50-d8_512x512_80k_ade20k.py - Name: nonlocal_r50-d8_512x512_80k_ade20k
In Collection: nonlocal_net In Collection: nonlocal_net
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 46.79
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 46.79
lr schd: 80000
memory (GB): 9.1 memory (GB): 9.1
Name: nonlocal_r50-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 40.75 mIoU: 40.75
mIoU(ms+flip): 42.05 mIoU(ms+flip): 42.05
Task: Semantic Segmentation Config: configs/nonlocal_net/nonlocal_r50-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_80k_ade20k/nonlocal_r50-d8_512x512_80k_ade20k_20200615_015801-5ae0aa33.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_80k_ade20k/nonlocal_r50-d8_512x512_80k_ade20k_20200615_015801-5ae0aa33.pth
- Config: configs/nonlocal_net/nonlocal_r101-d8_512x512_80k_ade20k.py - Name: nonlocal_r101-d8_512x512_80k_ade20k
In Collection: nonlocal_net In Collection: nonlocal_net
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 71.58
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 71.58
lr schd: 80000
memory (GB): 12.6 memory (GB): 12.6
Name: nonlocal_r101-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.9 mIoU: 42.9
mIoU(ms+flip): 44.27 mIoU(ms+flip): 44.27
Task: Semantic Segmentation Config: configs/nonlocal_net/nonlocal_r101-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_80k_ade20k/nonlocal_r101-d8_512x512_80k_ade20k_20200615_015758-24105919.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_80k_ade20k/nonlocal_r101-d8_512x512_80k_ade20k_20200615_015758-24105919.pth
- Config: configs/nonlocal_net/nonlocal_r50-d8_512x512_160k_ade20k.py - Name: nonlocal_r50-d8_512x512_160k_ade20k
In Collection: nonlocal_net In Collection: nonlocal_net
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: nonlocal_r50-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.03 mIoU: 42.03
mIoU(ms+flip): 43.04 mIoU(ms+flip): 43.04
Task: Semantic Segmentation Config: configs/nonlocal_net/nonlocal_r50-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_160k_ade20k/nonlocal_r50-d8_512x512_160k_ade20k_20200616_005410-baef45e3.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_160k_ade20k/nonlocal_r50-d8_512x512_160k_ade20k_20200616_005410-baef45e3.pth
- Config: configs/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k.py - Name: nonlocal_r101-d8_512x512_160k_ade20k
In Collection: nonlocal_net In Collection: nonlocal_net
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: nonlocal_r101-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 44.63 mIoU: 44.63
mIoU(ms+flip): 45.79 mIoU(ms+flip): 45.79
Task: Semantic Segmentation Config: configs/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20210827_221502-7881aa1a.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20210827_221502-7881aa1a.pth
- Config: configs/nonlocal_net/nonlocal_r50-d8_512x512_20k_voc12aug.py - Name: nonlocal_r50-d8_512x512_20k_voc12aug
In Collection: nonlocal_net In Collection: nonlocal_net
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 47.15
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 47.15
lr schd: 20000
memory (GB): 6.4 memory (GB): 6.4
Name: nonlocal_r50-d8_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 76.2 mIoU: 76.2
mIoU(ms+flip): 77.12 mIoU(ms+flip): 77.12
Task: Semantic Segmentation Config: configs/nonlocal_net/nonlocal_r50-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_20k_voc12aug/nonlocal_r50-d8_512x512_20k_voc12aug_20200617_222613-07f2a57c.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_20k_voc12aug/nonlocal_r50-d8_512x512_20k_voc12aug_20200617_222613-07f2a57c.pth
- Config: configs/nonlocal_net/nonlocal_r101-d8_512x512_20k_voc12aug.py - Name: nonlocal_r101-d8_512x512_20k_voc12aug
In Collection: nonlocal_net In Collection: nonlocal_net
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 71.38
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 71.38
lr schd: 20000
memory (GB): 9.8 memory (GB): 9.8
Name: nonlocal_r101-d8_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 78.15 mIoU: 78.15
mIoU(ms+flip): 78.86 mIoU(ms+flip): 78.86
Task: Semantic Segmentation Config: configs/nonlocal_net/nonlocal_r101-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_20k_voc12aug/nonlocal_r101-d8_512x512_20k_voc12aug_20200617_222615-948c68ab.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_20k_voc12aug/nonlocal_r101-d8_512x512_20k_voc12aug_20200617_222615-948c68ab.pth
- Config: configs/nonlocal_net/nonlocal_r50-d8_512x512_40k_voc12aug.py - Name: nonlocal_r50-d8_512x512_40k_voc12aug
In Collection: nonlocal_net In Collection: nonlocal_net
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: nonlocal_r50-d8_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 76.65 mIoU: 76.65
mIoU(ms+flip): 77.47 mIoU(ms+flip): 77.47
Task: Semantic Segmentation Config: configs/nonlocal_net/nonlocal_r50-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_40k_voc12aug/nonlocal_r50-d8_512x512_40k_voc12aug_20200614_000028-0139d4a9.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_40k_voc12aug/nonlocal_r50-d8_512x512_40k_voc12aug_20200614_000028-0139d4a9.pth
- Config: configs/nonlocal_net/nonlocal_r101-d8_512x512_40k_voc12aug.py - Name: nonlocal_r101-d8_512x512_40k_voc12aug
In Collection: nonlocal_net In Collection: nonlocal_net
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: nonlocal_r101-d8_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 78.27 mIoU: 78.27
mIoU(ms+flip): 79.12 mIoU(ms+flip): 79.12
Task: Semantic Segmentation Config: configs/nonlocal_net/nonlocal_r101-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_40k_voc12aug/nonlocal_r101-d8_512x512_40k_voc12aug_20200614_000028-7e5ff470.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_40k_voc12aug/nonlocal_r101-d8_512x512_40k_voc12aug_20200614_000028-7e5ff470.pth

9
configs/ocrnet/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/openseg-group/OCNet.pytorch">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1909.11065">OCRNet (ECCV'2020)</a></summary>
```latex ```latex
@article{YuanW18, @article{YuanW18,
title={Ocnet: Object context network for scene parsing}, title={Ocnet: Object context network for scene parsing},
@ -20,6 +27,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

271
configs/ocrnet/ocrnet.yml
View File

@ -1,431 +1,438 @@
Collections: Collections:
- Metadata: - Name: ocrnet
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ' HRNet backbone'
- ' ResNet backbone'
- ADE20K - ADE20K
- Pascal VOC 2012 + Aug - Pascal VOC 2012 + Aug
Name: ocrnet Paper:
URL: https://arxiv.org/abs/1909.11065
Title: Object-Contextual Representations for Semantic Segmentation
README: configs/ocrnet/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/ocr_head.py#L86
Version: v0.17.0
Converted From:
Code: https://github.com/openseg-group/OCNet.pytorch
Models: Models:
- Config: configs/ocrnet/ocrnet_hr18s_512x1024_40k_cityscapes.py - Name: ocrnet_hr18s_512x1024_40k_cityscapes
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W18-Small backbone: HRNetV2p-W18-Small
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 95.69
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 95.69
lr schd: 40000
memory (GB): 3.5 memory (GB): 3.5
Name: ocrnet_hr18s_512x1024_40k_cityscapes
Results: Results:
Dataset: ' HRNet backbone' - Task: Semantic Segmentation
Dataset: Cityscapes
Metrics: Metrics:
mIoU: 74.3 mIoU: 74.3
mIoU(ms+flip): 75.95 mIoU(ms+flip): 75.95
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr18s_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_40k_cityscapes/ocrnet_hr18s_512x1024_40k_cityscapes_20200601_033304-fa2436c2.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_40k_cityscapes/ocrnet_hr18s_512x1024_40k_cityscapes_20200601_033304-fa2436c2.pth
- Config: configs/ocrnet/ocrnet_hr18_512x1024_40k_cityscapes.py - Name: ocrnet_hr18_512x1024_40k_cityscapes
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W18 backbone: HRNetV2p-W18
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 133.33
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 133.33
lr schd: 40000
memory (GB): 4.7 memory (GB): 4.7
Name: ocrnet_hr18_512x1024_40k_cityscapes
Results: Results:
Dataset: ' HRNet backbone' - Task: Semantic Segmentation
Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.72 mIoU: 77.72
mIoU(ms+flip): 79.49 mIoU(ms+flip): 79.49
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr18_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_40k_cityscapes/ocrnet_hr18_512x1024_40k_cityscapes_20200601_033320-401c5bdd.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_40k_cityscapes/ocrnet_hr18_512x1024_40k_cityscapes_20200601_033320-401c5bdd.pth
- Config: configs/ocrnet/ocrnet_hr48_512x1024_40k_cityscapes.py - Name: ocrnet_hr48_512x1024_40k_cityscapes
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W48 backbone: HRNetV2p-W48
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 236.97
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 236.97
lr schd: 40000
memory (GB): 8.0 memory (GB): 8.0
Name: ocrnet_hr48_512x1024_40k_cityscapes
Results: Results:
Dataset: ' HRNet backbone' - Task: Semantic Segmentation
Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.58 mIoU: 80.58
mIoU(ms+flip): 81.79 mIoU(ms+flip): 81.79
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr48_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_40k_cityscapes/ocrnet_hr48_512x1024_40k_cityscapes_20200601_033336-55b32491.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_40k_cityscapes/ocrnet_hr48_512x1024_40k_cityscapes_20200601_033336-55b32491.pth
- Config: configs/ocrnet/ocrnet_hr18s_512x1024_80k_cityscapes.py - Name: ocrnet_hr18s_512x1024_80k_cityscapes
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W18-Small backbone: HRNetV2p-W18-Small
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: ocrnet_hr18s_512x1024_80k_cityscapes
Results: Results:
Dataset: ' HRNet backbone' - Task: Semantic Segmentation
Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.16 mIoU: 77.16
mIoU(ms+flip): 78.66 mIoU(ms+flip): 78.66
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr18s_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_80k_cityscapes/ocrnet_hr18s_512x1024_80k_cityscapes_20200601_222735-55979e63.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_80k_cityscapes/ocrnet_hr18s_512x1024_80k_cityscapes_20200601_222735-55979e63.pth
- Config: configs/ocrnet/ocrnet_hr18_512x1024_80k_cityscapes.py - Name: ocrnet_hr18_512x1024_80k_cityscapes
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W18 backbone: HRNetV2p-W18
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: ocrnet_hr18_512x1024_80k_cityscapes
Results: Results:
Dataset: ' HRNet backbone' - Task: Semantic Segmentation
Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.57 mIoU: 78.57
mIoU(ms+flip): 80.46 mIoU(ms+flip): 80.46
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr18_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_80k_cityscapes/ocrnet_hr18_512x1024_80k_cityscapes_20200614_230521-c2e1dd4a.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_80k_cityscapes/ocrnet_hr18_512x1024_80k_cityscapes_20200614_230521-c2e1dd4a.pth
- Config: configs/ocrnet/ocrnet_hr48_512x1024_80k_cityscapes.py - Name: ocrnet_hr48_512x1024_80k_cityscapes
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W48 backbone: HRNetV2p-W48
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: ocrnet_hr48_512x1024_80k_cityscapes
Results: Results:
Dataset: ' HRNet backbone' - Task: Semantic Segmentation
Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.7 mIoU: 80.7
mIoU(ms+flip): 81.87 mIoU(ms+flip): 81.87
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr48_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_80k_cityscapes/ocrnet_hr48_512x1024_80k_cityscapes_20200601_222752-9076bcdf.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_80k_cityscapes/ocrnet_hr48_512x1024_80k_cityscapes_20200601_222752-9076bcdf.pth
- Config: configs/ocrnet/ocrnet_hr18s_512x1024_160k_cityscapes.py - Name: ocrnet_hr18s_512x1024_160k_cityscapes
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W18-Small backbone: HRNetV2p-W18-Small
crop size: (512,1024) crop size: (512,1024)
lr schd: 160000 lr schd: 160000
Name: ocrnet_hr18s_512x1024_160k_cityscapes
Results: Results:
Dataset: ' HRNet backbone' - Task: Semantic Segmentation
Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.45 mIoU: 78.45
mIoU(ms+flip): 79.97 mIoU(ms+flip): 79.97
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr18s_512x1024_160k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_160k_cityscapes/ocrnet_hr18s_512x1024_160k_cityscapes_20200602_191005-f4a7af28.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x1024_160k_cityscapes/ocrnet_hr18s_512x1024_160k_cityscapes_20200602_191005-f4a7af28.pth
- Config: configs/ocrnet/ocrnet_hr18_512x1024_160k_cityscapes.py - Name: ocrnet_hr18_512x1024_160k_cityscapes
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W18 backbone: HRNetV2p-W18
crop size: (512,1024) crop size: (512,1024)
lr schd: 160000 lr schd: 160000
Name: ocrnet_hr18_512x1024_160k_cityscapes
Results: Results:
Dataset: ' HRNet backbone' - Task: Semantic Segmentation
Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.47 mIoU: 79.47
mIoU(ms+flip): 80.91 mIoU(ms+flip): 80.91
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr18_512x1024_160k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_160k_cityscapes/ocrnet_hr18_512x1024_160k_cityscapes_20200602_191001-b9172d0c.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x1024_160k_cityscapes/ocrnet_hr18_512x1024_160k_cityscapes_20200602_191001-b9172d0c.pth
- Config: configs/ocrnet/ocrnet_hr48_512x1024_160k_cityscapes.py - Name: ocrnet_hr48_512x1024_160k_cityscapes
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W48 backbone: HRNetV2p-W48
crop size: (512,1024) crop size: (512,1024)
lr schd: 160000 lr schd: 160000
Name: ocrnet_hr48_512x1024_160k_cityscapes
Results: Results:
Dataset: ' HRNet backbone' - Task: Semantic Segmentation
Dataset: Cityscapes
Metrics: Metrics:
mIoU: 81.35 mIoU: 81.35
mIoU(ms+flip): 82.7 mIoU(ms+flip): 82.7
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr48_512x1024_160k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_160k_cityscapes/ocrnet_hr48_512x1024_160k_cityscapes_20200602_191037-dfbf1b0c.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x1024_160k_cityscapes/ocrnet_hr48_512x1024_160k_cityscapes_20200602_191037-dfbf1b0c.pth
- Config: configs/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes.py - Name: ocrnet_r101-d8_512x1024_40k_b8_cityscapes
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000 lr schd: 40000
Name: ocrnet_r101-d8_512x1024_40k_b8_cityscapes
Results: Results:
Dataset: ' ResNet backbone' - Task: Semantic Segmentation
Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.09 mIoU: 80.09
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes_20200717_110721-02ac0f13.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes_20200717_110721-02ac0f13.pth
- Config: configs/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes.py - Name: ocrnet_r101-d8_512x1024_40k_b16_cityscapes
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 331.13
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 331.13
lr schd: 40000
memory (GB): 8.8 memory (GB): 8.8
Name: ocrnet_r101-d8_512x1024_40k_b16_cityscapes
Results: Results:
Dataset: ' ResNet backbone' - Task: Semantic Segmentation
Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.3 mIoU: 80.3
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes_20200723_193726-db500f80.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes_20200723_193726-db500f80.pth
- Config: configs/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes.py - Name: ocrnet_r101-d8_512x1024_80k_b16_cityscapes
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 331.13
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 331.13
lr schd: 80000
memory (GB): 8.8 memory (GB): 8.8
Name: ocrnet_r101-d8_512x1024_80k_b16_cityscapes
Results: Results:
Dataset: ' ResNet backbone' - Task: Semantic Segmentation
Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.81 mIoU: 80.81
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes_20200723_192421-78688424.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes_20200723_192421-78688424.pth
- Config: configs/ocrnet/ocrnet_hr18s_512x512_80k_ade20k.py - Name: ocrnet_hr18s_512x512_80k_ade20k
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W18-Small backbone: HRNetV2p-W18-Small
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 34.51
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 34.51
lr schd: 80000
memory (GB): 6.7 memory (GB): 6.7
Name: ocrnet_hr18s_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 35.06 mIoU: 35.06
mIoU(ms+flip): 35.8 mIoU(ms+flip): 35.8
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr18s_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_80k_ade20k/ocrnet_hr18s_512x512_80k_ade20k_20200615_055600-e80b62af.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_80k_ade20k/ocrnet_hr18s_512x512_80k_ade20k_20200615_055600-e80b62af.pth
- Config: configs/ocrnet/ocrnet_hr18_512x512_80k_ade20k.py - Name: ocrnet_hr18_512x512_80k_ade20k
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W18 backbone: HRNetV2p-W18
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 52.83
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 52.83
lr schd: 80000
memory (GB): 7.9 memory (GB): 7.9
Name: ocrnet_hr18_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 37.79 mIoU: 37.79
mIoU(ms+flip): 39.16 mIoU(ms+flip): 39.16
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr18_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_80k_ade20k/ocrnet_hr18_512x512_80k_ade20k_20200615_053157-d173d83b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_80k_ade20k/ocrnet_hr18_512x512_80k_ade20k_20200615_053157-d173d83b.pth
- Config: configs/ocrnet/ocrnet_hr48_512x512_80k_ade20k.py - Name: ocrnet_hr48_512x512_80k_ade20k
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W48 backbone: HRNetV2p-W48
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 58.86
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 58.86
lr schd: 80000
memory (GB): 11.2 memory (GB): 11.2
Name: ocrnet_hr48_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 43.0 mIoU: 43.0
mIoU(ms+flip): 44.3 mIoU(ms+flip): 44.3
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr48_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_80k_ade20k/ocrnet_hr48_512x512_80k_ade20k_20200615_021518-d168c2d1.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_80k_ade20k/ocrnet_hr48_512x512_80k_ade20k_20200615_021518-d168c2d1.pth
- Config: configs/ocrnet/ocrnet_hr18s_512x512_160k_ade20k.py - Name: ocrnet_hr18s_512x512_160k_ade20k
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W18-Small backbone: HRNetV2p-W18-Small
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: ocrnet_hr18s_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 37.19 mIoU: 37.19
mIoU(ms+flip): 38.4 mIoU(ms+flip): 38.4
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr18s_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_160k_ade20k/ocrnet_hr18s_512x512_160k_ade20k_20200615_184505-8e913058.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_160k_ade20k/ocrnet_hr18s_512x512_160k_ade20k_20200615_184505-8e913058.pth
- Config: configs/ocrnet/ocrnet_hr18_512x512_160k_ade20k.py - Name: ocrnet_hr18_512x512_160k_ade20k
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W18 backbone: HRNetV2p-W18
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: ocrnet_hr18_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 39.32 mIoU: 39.32
mIoU(ms+flip): 40.8 mIoU(ms+flip): 40.8
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr18_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_160k_ade20k/ocrnet_hr18_512x512_160k_ade20k_20200615_200940-d8fcd9d1.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_160k_ade20k/ocrnet_hr18_512x512_160k_ade20k_20200615_200940-d8fcd9d1.pth
- Config: configs/ocrnet/ocrnet_hr48_512x512_160k_ade20k.py - Name: ocrnet_hr48_512x512_160k_ade20k
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W48 backbone: HRNetV2p-W48
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: ocrnet_hr48_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 43.25 mIoU: 43.25
mIoU(ms+flip): 44.88 mIoU(ms+flip): 44.88
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr48_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_160k_ade20k/ocrnet_hr48_512x512_160k_ade20k_20200615_184705-a073726d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_160k_ade20k/ocrnet_hr48_512x512_160k_ade20k_20200615_184705-a073726d.pth
- Config: configs/ocrnet/ocrnet_hr18s_512x512_20k_voc12aug.py - Name: ocrnet_hr18s_512x512_20k_voc12aug
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W18-Small backbone: HRNetV2p-W18-Small
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 31.7
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 31.7
lr schd: 20000
memory (GB): 3.5 memory (GB): 3.5
Name: ocrnet_hr18s_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 71.7 mIoU: 71.7
mIoU(ms+flip): 73.84 mIoU(ms+flip): 73.84
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr18s_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_20k_voc12aug/ocrnet_hr18s_512x512_20k_voc12aug_20200617_233913-02b04fcb.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_20k_voc12aug/ocrnet_hr18s_512x512_20k_voc12aug_20200617_233913-02b04fcb.pth
- Config: configs/ocrnet/ocrnet_hr18_512x512_20k_voc12aug.py - Name: ocrnet_hr18_512x512_20k_voc12aug
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W18 backbone: HRNetV2p-W18
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 50.23
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 50.23
lr schd: 20000
memory (GB): 4.7 memory (GB): 4.7
Name: ocrnet_hr18_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 74.75 mIoU: 74.75
mIoU(ms+flip): 77.11 mIoU(ms+flip): 77.11
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr18_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_20k_voc12aug/ocrnet_hr18_512x512_20k_voc12aug_20200617_233932-8954cbb7.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_20k_voc12aug/ocrnet_hr18_512x512_20k_voc12aug_20200617_233932-8954cbb7.pth
- Config: configs/ocrnet/ocrnet_hr48_512x512_20k_voc12aug.py - Name: ocrnet_hr48_512x512_20k_voc12aug
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W48 backbone: HRNetV2p-W48
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 56.09
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 56.09
lr schd: 20000
memory (GB): 8.1 memory (GB): 8.1
Name: ocrnet_hr48_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 77.72 mIoU: 77.72
mIoU(ms+flip): 79.87 mIoU(ms+flip): 79.87
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr48_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_20k_voc12aug/ocrnet_hr48_512x512_20k_voc12aug_20200617_233932-9e82080a.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_20k_voc12aug/ocrnet_hr48_512x512_20k_voc12aug_20200617_233932-9e82080a.pth
- Config: configs/ocrnet/ocrnet_hr18s_512x512_40k_voc12aug.py - Name: ocrnet_hr18s_512x512_40k_voc12aug
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W18-Small backbone: HRNetV2p-W18-Small
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: ocrnet_hr18s_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 72.76 mIoU: 72.76
mIoU(ms+flip): 74.6 mIoU(ms+flip): 74.6
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr18s_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_40k_voc12aug/ocrnet_hr18s_512x512_40k_voc12aug_20200614_002025-42b587ac.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18s_512x512_40k_voc12aug/ocrnet_hr18s_512x512_40k_voc12aug_20200614_002025-42b587ac.pth
- Config: configs/ocrnet/ocrnet_hr18_512x512_40k_voc12aug.py - Name: ocrnet_hr18_512x512_40k_voc12aug
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W18 backbone: HRNetV2p-W18
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: ocrnet_hr18_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 74.98 mIoU: 74.98
mIoU(ms+flip): 77.4 mIoU(ms+flip): 77.4
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr18_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_40k_voc12aug/ocrnet_hr18_512x512_40k_voc12aug_20200614_015958-714302be.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr18_512x512_40k_voc12aug/ocrnet_hr18_512x512_40k_voc12aug_20200614_015958-714302be.pth
- Config: configs/ocrnet/ocrnet_hr48_512x512_40k_voc12aug.py - Name: ocrnet_hr48_512x512_40k_voc12aug
In Collection: ocrnet In Collection: ocrnet
Metadata: Metadata:
backbone: HRNetV2p-W48 backbone: HRNetV2p-W48
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: ocrnet_hr48_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 77.14 mIoU: 77.14
mIoU(ms+flip): 79.71 mIoU(ms+flip): 79.71
Task: Semantic Segmentation Config: configs/ocrnet/ocrnet_hr48_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_40k_voc12aug/ocrnet_hr48_512x512_40k_voc12aug_20200614_015958-255bc5ce.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_hr48_512x512_40k_voc12aug/ocrnet_hr48_512x512_40k_voc12aug_20200614_015958-255bc5ce.pth

9
configs/point_rend/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/facebookresearch/detectron2/tree/master/projects/PointRend">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/point_head.py#L36">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1912.08193">PointRend (CVPR'2020)</a></summary>
``` ```
@inproceedings{kirillov2020pointrend, @inproceedings{kirillov2020pointrend,
title={Pointrend: Image segmentation as rendering}, title={Pointrend: Image segmentation as rendering},
@ -14,6 +21,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

69
configs/point_rend/point_rend.yml
View File

@ -1,95 +1,104 @@
Collections: Collections:
- Metadata: - Name: point_rend
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20K - ADE20K
Name: point_rend Paper:
URL: https://arxiv.org/abs/1912.08193
Title: 'PointRend: Image Segmentation as Rendering'
README: configs/point_rend/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/point_head.py#L36
Version: v0.17.0
Converted From:
Code: https://github.com/facebookresearch/detectron2/tree/master/projects/PointRend
Models: Models:
- Config: configs/point_rend/pointrend_r50_512x1024_80k_cityscapes.py - Name: pointrend_r50_512x1024_80k_cityscapes
In Collection: point_rend In Collection: point_rend
Metadata: Metadata:
backbone: R-50 backbone: R-50
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 117.92
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 117.92
lr schd: 80000
memory (GB): 3.1 memory (GB): 3.1
Name: pointrend_r50_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 76.47 mIoU: 76.47
mIoU(ms+flip): 78.13 mIoU(ms+flip): 78.13
Task: Semantic Segmentation Config: configs/point_rend/pointrend_r50_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x1024_80k_cityscapes/pointrend_r50_512x1024_80k_cityscapes_20200711_015821-bb1ff523.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x1024_80k_cityscapes/pointrend_r50_512x1024_80k_cityscapes_20200711_015821-bb1ff523.pth
- Config: configs/point_rend/pointrend_r101_512x1024_80k_cityscapes.py - Name: pointrend_r101_512x1024_80k_cityscapes
In Collection: point_rend In Collection: point_rend
Metadata: Metadata:
backbone: R-101 backbone: R-101
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 142.86
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 142.86
lr schd: 80000
memory (GB): 4.2 memory (GB): 4.2
Name: pointrend_r101_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.3 mIoU: 78.3
mIoU(ms+flip): 79.97 mIoU(ms+flip): 79.97
Task: Semantic Segmentation Config: configs/point_rend/pointrend_r101_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x1024_80k_cityscapes/pointrend_r101_512x1024_80k_cityscapes_20200711_170850-d0ca84be.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x1024_80k_cityscapes/pointrend_r101_512x1024_80k_cityscapes_20200711_170850-d0ca84be.pth
- Config: configs/point_rend/pointrend_r50_512x512_160k_ade20k.py - Name: pointrend_r50_512x512_160k_ade20k
In Collection: point_rend In Collection: point_rend
Metadata: Metadata:
backbone: R-50 backbone: R-50
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 57.77
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 57.77
lr schd: 160000
memory (GB): 5.1 memory (GB): 5.1
Name: pointrend_r50_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 37.64 mIoU: 37.64
mIoU(ms+flip): 39.17 mIoU(ms+flip): 39.17
Task: Semantic Segmentation Config: configs/point_rend/pointrend_r50_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x512_160k_ade20k/pointrend_r50_512x512_160k_ade20k_20200807_232644-ac3febf2.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r50_512x512_160k_ade20k/pointrend_r50_512x512_160k_ade20k_20200807_232644-ac3febf2.pth
- Config: configs/point_rend/pointrend_r101_512x512_160k_ade20k.py - Name: pointrend_r101_512x512_160k_ade20k
In Collection: point_rend In Collection: point_rend
Metadata: Metadata:
backbone: R-101 backbone: R-101
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 64.52
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 64.52
lr schd: 160000
memory (GB): 6.1 memory (GB): 6.1
Name: pointrend_r101_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 40.02 mIoU: 40.02
mIoU(ms+flip): 41.6 mIoU(ms+flip): 41.6
Task: Semantic Segmentation Config: configs/point_rend/pointrend_r101_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x512_160k_ade20k/pointrend_r101_512x512_160k_ade20k_20200808_030852-8834902a.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/point_rend/pointrend_r101_512x512_160k_ade20k/pointrend_r101_512x512_160k_ade20k_20200808_030852-8834902a.pth

9
configs/psanet/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/hszhao/PSANet">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18">Code Snippet</a>
<details>
<summary align="right"><a href="https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf">PSANet (ECCV'2018)</a></summary>
```latex ```latex
@inproceedings{zhao2018psanet, @inproceedings{zhao2018psanet,
title={Psanet: Point-wise spatial attention network for scene parsing}, title={Psanet: Point-wise spatial attention network for scene parsing},
@ -14,6 +21,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

173
configs/psanet/psanet.yml
View File

@ -1,296 +1,305 @@
Collections: Collections:
- Metadata: - Name: psanet
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20K - ADE20K
- Pascal VOC 2012 + Aug - Pascal VOC 2012 + Aug
Name: psanet Paper:
URL: https://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf
Title: 'PSANet: Point-wise Spatial Attention Network for Scene Parsing'
README: configs/psanet/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psa_head.py#L18
Version: v0.17.0
Converted From:
Code: https://github.com/hszhao/PSANet
Models: Models:
- Config: configs/psanet/psanet_r50-d8_512x1024_40k_cityscapes.py - Name: psanet_r50-d8_512x1024_40k_cityscapes
In Collection: psanet In Collection: psanet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 315.46
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 315.46
lr schd: 40000
memory (GB): 7.0 memory (GB): 7.0
Name: psanet_r50-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.63 mIoU: 77.63
mIoU(ms+flip): 79.04 mIoU(ms+flip): 79.04
Task: Semantic Segmentation Config: configs/psanet/psanet_r50-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_40k_cityscapes/psanet_r50-d8_512x1024_40k_cityscapes_20200606_103117-99fac37c.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_40k_cityscapes/psanet_r50-d8_512x1024_40k_cityscapes_20200606_103117-99fac37c.pth
- Config: configs/psanet/psanet_r101-d8_512x1024_40k_cityscapes.py - Name: psanet_r101-d8_512x1024_40k_cityscapes
In Collection: psanet In Collection: psanet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 454.55
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 454.55
lr schd: 40000
memory (GB): 10.5 memory (GB): 10.5
Name: psanet_r101-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.14 mIoU: 79.14
mIoU(ms+flip): 80.19 mIoU(ms+flip): 80.19
Task: Semantic Segmentation Config: configs/psanet/psanet_r101-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_40k_cityscapes/psanet_r101-d8_512x1024_40k_cityscapes_20200606_001418-27b9cfa7.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_40k_cityscapes/psanet_r101-d8_512x1024_40k_cityscapes_20200606_001418-27b9cfa7.pth
- Config: configs/psanet/psanet_r50-d8_769x769_40k_cityscapes.py - Name: psanet_r50-d8_769x769_40k_cityscapes
In Collection: psanet In Collection: psanet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 714.29
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 714.29
lr schd: 40000
memory (GB): 7.9 memory (GB): 7.9
Name: psanet_r50-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.99 mIoU: 77.99
mIoU(ms+flip): 79.64 mIoU(ms+flip): 79.64
Task: Semantic Segmentation Config: configs/psanet/psanet_r50-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_40k_cityscapes/psanet_r50-d8_769x769_40k_cityscapes_20200530_033717-d5365506.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_40k_cityscapes/psanet_r50-d8_769x769_40k_cityscapes_20200530_033717-d5365506.pth
- Config: configs/psanet/psanet_r101-d8_769x769_40k_cityscapes.py - Name: psanet_r101-d8_769x769_40k_cityscapes
In Collection: psanet In Collection: psanet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 1020.41
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 1020.41
lr schd: 40000
memory (GB): 11.9 memory (GB): 11.9
Name: psanet_r101-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.43 mIoU: 78.43
mIoU(ms+flip): 80.26 mIoU(ms+flip): 80.26
Task: Semantic Segmentation Config: configs/psanet/psanet_r101-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_40k_cityscapes/psanet_r101-d8_769x769_40k_cityscapes_20200530_035107-997da1e6.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_40k_cityscapes/psanet_r101-d8_769x769_40k_cityscapes_20200530_035107-997da1e6.pth
- Config: configs/psanet/psanet_r50-d8_512x1024_80k_cityscapes.py - Name: psanet_r50-d8_512x1024_80k_cityscapes
In Collection: psanet In Collection: psanet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: psanet_r50-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.24 mIoU: 77.24
mIoU(ms+flip): 78.69 mIoU(ms+flip): 78.69
Task: Semantic Segmentation Config: configs/psanet/psanet_r50-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_80k_cityscapes/psanet_r50-d8_512x1024_80k_cityscapes_20200606_161842-ab60a24f.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x1024_80k_cityscapes/psanet_r50-d8_512x1024_80k_cityscapes_20200606_161842-ab60a24f.pth
- Config: configs/psanet/psanet_r101-d8_512x1024_80k_cityscapes.py - Name: psanet_r101-d8_512x1024_80k_cityscapes
In Collection: psanet In Collection: psanet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: psanet_r101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.31 mIoU: 79.31
mIoU(ms+flip): 80.53 mIoU(ms+flip): 80.53
Task: Semantic Segmentation Config: configs/psanet/psanet_r101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_80k_cityscapes/psanet_r101-d8_512x1024_80k_cityscapes_20200606_161823-0f73a169.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x1024_80k_cityscapes/psanet_r101-d8_512x1024_80k_cityscapes_20200606_161823-0f73a169.pth
- Config: configs/psanet/psanet_r50-d8_769x769_80k_cityscapes.py - Name: psanet_r50-d8_769x769_80k_cityscapes
In Collection: psanet In Collection: psanet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: psanet_r50-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.31 mIoU: 79.31
mIoU(ms+flip): 80.91 mIoU(ms+flip): 80.91
Task: Semantic Segmentation Config: configs/psanet/psanet_r50-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_80k_cityscapes/psanet_r50-d8_769x769_80k_cityscapes_20200606_225134-fe42f49e.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_769x769_80k_cityscapes/psanet_r50-d8_769x769_80k_cityscapes_20200606_225134-fe42f49e.pth
- Config: configs/psanet/psanet_r101-d8_769x769_80k_cityscapes.py - Name: psanet_r101-d8_769x769_80k_cityscapes
In Collection: psanet In Collection: psanet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: psanet_r101-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.69 mIoU: 79.69
mIoU(ms+flip): 80.89 mIoU(ms+flip): 80.89
Task: Semantic Segmentation Config: configs/psanet/psanet_r101-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_80k_cityscapes/psanet_r101-d8_769x769_80k_cityscapes_20200606_214550-7665827b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_769x769_80k_cityscapes/psanet_r101-d8_769x769_80k_cityscapes_20200606_214550-7665827b.pth
- Config: configs/psanet/psanet_r50-d8_512x512_80k_ade20k.py - Name: psanet_r50-d8_512x512_80k_ade20k
In Collection: psanet In Collection: psanet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 52.88
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 52.88
lr schd: 80000
memory (GB): 9.0 memory (GB): 9.0
Name: psanet_r50-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 41.14 mIoU: 41.14
mIoU(ms+flip): 41.91 mIoU(ms+flip): 41.91
Task: Semantic Segmentation Config: configs/psanet/psanet_r50-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_80k_ade20k/psanet_r50-d8_512x512_80k_ade20k_20200614_144141-835e4b97.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_80k_ade20k/psanet_r50-d8_512x512_80k_ade20k_20200614_144141-835e4b97.pth
- Config: configs/psanet/psanet_r101-d8_512x512_80k_ade20k.py - Name: psanet_r101-d8_512x512_80k_ade20k
In Collection: psanet In Collection: psanet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 76.16
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 76.16
lr schd: 80000
memory (GB): 12.5 memory (GB): 12.5
Name: psanet_r101-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 43.8 mIoU: 43.8
mIoU(ms+flip): 44.75 mIoU(ms+flip): 44.75
Task: Semantic Segmentation Config: configs/psanet/psanet_r101-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_80k_ade20k/psanet_r101-d8_512x512_80k_ade20k_20200614_185117-1fab60d4.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_80k_ade20k/psanet_r101-d8_512x512_80k_ade20k_20200614_185117-1fab60d4.pth
- Config: configs/psanet/psanet_r50-d8_512x512_160k_ade20k.py - Name: psanet_r50-d8_512x512_160k_ade20k
In Collection: psanet In Collection: psanet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: psanet_r50-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 41.67 mIoU: 41.67
mIoU(ms+flip): 42.95 mIoU(ms+flip): 42.95
Task: Semantic Segmentation Config: configs/psanet/psanet_r50-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_160k_ade20k/psanet_r50-d8_512x512_160k_ade20k_20200615_161258-148077dd.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_160k_ade20k/psanet_r50-d8_512x512_160k_ade20k_20200615_161258-148077dd.pth
- Config: configs/psanet/psanet_r101-d8_512x512_160k_ade20k.py - Name: psanet_r101-d8_512x512_160k_ade20k
In Collection: psanet In Collection: psanet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: psanet_r101-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 43.74 mIoU: 43.74
mIoU(ms+flip): 45.38 mIoU(ms+flip): 45.38
Task: Semantic Segmentation Config: configs/psanet/psanet_r101-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_160k_ade20k/psanet_r101-d8_512x512_160k_ade20k_20200615_161537-dbfa564c.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_160k_ade20k/psanet_r101-d8_512x512_160k_ade20k_20200615_161537-dbfa564c.pth
- Config: configs/psanet/psanet_r50-d8_512x512_20k_voc12aug.py - Name: psanet_r50-d8_512x512_20k_voc12aug
In Collection: psanet In Collection: psanet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 54.82
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 54.82
lr schd: 20000
memory (GB): 6.9 memory (GB): 6.9
Name: psanet_r50-d8_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 76.39 mIoU: 76.39
mIoU(ms+flip): 77.34 mIoU(ms+flip): 77.34
Task: Semantic Segmentation Config: configs/psanet/psanet_r50-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_20k_voc12aug/psanet_r50-d8_512x512_20k_voc12aug_20200617_102413-2f1bbaa1.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_20k_voc12aug/psanet_r50-d8_512x512_20k_voc12aug_20200617_102413-2f1bbaa1.pth
- Config: configs/psanet/psanet_r101-d8_512x512_20k_voc12aug.py - Name: psanet_r101-d8_512x512_20k_voc12aug
In Collection: psanet In Collection: psanet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 79.18
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 79.18
lr schd: 20000
memory (GB): 10.4 memory (GB): 10.4
Name: psanet_r101-d8_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 77.91 mIoU: 77.91
mIoU(ms+flip): 79.3 mIoU(ms+flip): 79.3
Task: Semantic Segmentation Config: configs/psanet/psanet_r101-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_20k_voc12aug/psanet_r101-d8_512x512_20k_voc12aug_20200617_110624-946fef11.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_20k_voc12aug/psanet_r101-d8_512x512_20k_voc12aug_20200617_110624-946fef11.pth
- Config: configs/psanet/psanet_r50-d8_512x512_40k_voc12aug.py - Name: psanet_r50-d8_512x512_40k_voc12aug
In Collection: psanet In Collection: psanet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: psanet_r50-d8_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 76.3 mIoU: 76.3
mIoU(ms+flip): 77.35 mIoU(ms+flip): 77.35
Task: Semantic Segmentation Config: configs/psanet/psanet_r50-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_40k_voc12aug/psanet_r50-d8_512x512_40k_voc12aug_20200613_161946-f596afb5.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r50-d8_512x512_40k_voc12aug/psanet_r50-d8_512x512_40k_voc12aug_20200613_161946-f596afb5.pth
- Config: configs/psanet/psanet_r101-d8_512x512_40k_voc12aug.py - Name: psanet_r101-d8_512x512_40k_voc12aug
In Collection: psanet In Collection: psanet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: psanet_r101-d8_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 77.73 mIoU: 77.73
mIoU(ms+flip): 79.05 mIoU(ms+flip): 79.05
Task: Semantic Segmentation Config: configs/psanet/psanet_r101-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_40k_voc12aug/psanet_r101-d8_512x512_40k_voc12aug_20200613_161946-1f560f9e.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/psanet/psanet_r101-d8_512x512_40k_voc12aug/psanet_r101-d8_512x512_40k_voc12aug_20200613_161946-1f560f9e.pth

9
configs/pspnet/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/hszhao/PSPNet">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1612.01105">PSPNet (CVPR'2017)</a></summary>
```latex ```latex
@inproceedings{zhao2017pspnet, @inproceedings{zhao2017pspnet,
title={Pyramid Scene Parsing Network}, title={Pyramid Scene Parsing Network},
@ -13,6 +20,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

409
configs/pspnet/pspnet.yml
View File

@ -1,5 +1,6 @@
Collections: Collections:
- Metadata: - Name: pspnet
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20K - ADE20K
@ -9,705 +10,713 @@ Collections:
- Dark Zurich and Nighttime Driving - Dark Zurich and Nighttime Driving
- COCO-Stuff 10k - COCO-Stuff 10k
- COCO-Stuff 164k - COCO-Stuff 164k
Name: pspnet Paper:
URL: https://arxiv.org/abs/1612.01105
Title: Pyramid Scene Parsing Network
README: configs/pspnet/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/psp_head.py#L63
Version: v0.17.0
Converted From:
Code: https://github.com/hszhao/PSPNet
Models: Models:
- Config: configs/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes.py - Name: pspnet_r50-d8_512x1024_40k_cityscapes
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 245.7
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 245.7
lr schd: 40000
memory (GB): 6.1 memory (GB): 6.1
Name: pspnet_r50-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.85 mIoU: 77.85
mIoU(ms+flip): 79.18 mIoU(ms+flip): 79.18
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth
- Config: configs/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes.py - Name: pspnet_r101-d8_512x1024_40k_cityscapes
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 373.13
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 373.13
lr schd: 40000
memory (GB): 9.6 memory (GB): 9.6
Name: pspnet_r101-d8_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.34 mIoU: 78.34
mIoU(ms+flip): 79.74 mIoU(ms+flip): 79.74
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751-467e7cf4.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_40k_cityscapes/pspnet_r101-d8_512x1024_40k_cityscapes_20200604_232751-467e7cf4.pth
- Config: configs/pspnet/pspnet_r50-d8_769x769_40k_cityscapes.py - Name: pspnet_r50-d8_769x769_40k_cityscapes
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 568.18
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 568.18
lr schd: 40000
memory (GB): 6.9 memory (GB): 6.9
Name: pspnet_r50-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.26 mIoU: 78.26
mIoU(ms+flip): 79.88 mIoU(ms+flip): 79.88
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r50-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_40k_cityscapes/pspnet_r50-d8_769x769_40k_cityscapes_20200606_112725-86638686.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_40k_cityscapes/pspnet_r50-d8_769x769_40k_cityscapes_20200606_112725-86638686.pth
- Config: configs/pspnet/pspnet_r101-d8_769x769_40k_cityscapes.py - Name: pspnet_r101-d8_769x769_40k_cityscapes
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 869.57
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 869.57
lr schd: 40000
memory (GB): 10.9 memory (GB): 10.9
Name: pspnet_r101-d8_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.08 mIoU: 79.08
mIoU(ms+flip): 80.28 mIoU(ms+flip): 80.28
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101-d8_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_40k_cityscapes/pspnet_r101-d8_769x769_40k_cityscapes_20200606_112753-61c6f5be.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_40k_cityscapes/pspnet_r101-d8_769x769_40k_cityscapes_20200606_112753-61c6f5be.pth
- Config: configs/pspnet/pspnet_r18-d8_512x1024_80k_cityscapes.py - Name: pspnet_r18-d8_512x1024_80k_cityscapes
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-18-D8 backbone: R-18-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 63.65
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 63.65
lr schd: 80000
memory (GB): 1.7 memory (GB): 1.7
Name: pspnet_r18-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 74.87 mIoU: 74.87
mIoU(ms+flip): 76.04 mIoU(ms+flip): 76.04
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r18-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x1024_80k_cityscapes/pspnet_r18-d8_512x1024_80k_cityscapes_20201225_021458-09ffa746.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_512x1024_80k_cityscapes/pspnet_r18-d8_512x1024_80k_cityscapes_20201225_021458-09ffa746.pth
- Config: configs/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes.py - Name: pspnet_r50-d8_512x1024_80k_cityscapes
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: pspnet_r50-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.55 mIoU: 78.55
mIoU(ms+flip): 79.79 mIoU(ms+flip): 79.79
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_512x1024_80k_cityscapes_20200606_112131-2376f12b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes/pspnet_r50-d8_512x1024_80k_cityscapes_20200606_112131-2376f12b.pth
- Config: configs/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes.py - Name: pspnet_r101-d8_512x1024_80k_cityscapes
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: pspnet_r101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.76 mIoU: 79.76
mIoU(ms+flip): 81.01 mIoU(ms+flip): 81.01
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes/pspnet_r101-d8_512x1024_80k_cityscapes_20200606_112211-e1e1100f.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes/pspnet_r101-d8_512x1024_80k_cityscapes_20200606_112211-e1e1100f.pth
- Config: configs/pspnet/pspnet_r18-d8_769x769_80k_cityscapes.py - Name: pspnet_r18-d8_769x769_80k_cityscapes
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-18-D8 backbone: R-18-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 161.29
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 161.29
lr schd: 80000
memory (GB): 1.9 memory (GB): 1.9
Name: pspnet_r18-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 75.9 mIoU: 75.9
mIoU(ms+flip): 77.86 mIoU(ms+flip): 77.86
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r18-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_769x769_80k_cityscapes/pspnet_r18-d8_769x769_80k_cityscapes_20201225_021458-3deefc62.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_769x769_80k_cityscapes/pspnet_r18-d8_769x769_80k_cityscapes_20201225_021458-3deefc62.pth
- Config: configs/pspnet/pspnet_r50-d8_769x769_80k_cityscapes.py - Name: pspnet_r50-d8_769x769_80k_cityscapes
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: pspnet_r50-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.59 mIoU: 79.59
mIoU(ms+flip): 80.69 mIoU(ms+flip): 80.69
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r50-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_80k_cityscapes/pspnet_r50-d8_769x769_80k_cityscapes_20200606_210121-5ccf03dd.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_769x769_80k_cityscapes/pspnet_r50-d8_769x769_80k_cityscapes_20200606_210121-5ccf03dd.pth
- Config: configs/pspnet/pspnet_r101-d8_769x769_80k_cityscapes.py - Name: pspnet_r101-d8_769x769_80k_cityscapes
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: pspnet_r101-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.77 mIoU: 79.77
mIoU(ms+flip): 81.06 mIoU(ms+flip): 81.06
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_80k_cityscapes/pspnet_r101-d8_769x769_80k_cityscapes_20200606_225055-dba412fa.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_769x769_80k_cityscapes/pspnet_r101-d8_769x769_80k_cityscapes_20200606_225055-dba412fa.pth
- Config: configs/pspnet/pspnet_r18b-d8_512x1024_80k_cityscapes.py - Name: pspnet_r18b-d8_512x1024_80k_cityscapes
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-18b-D8 backbone: R-18b-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 61.43
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 61.43
lr schd: 80000
memory (GB): 1.5 memory (GB): 1.5
Name: pspnet_r18b-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 74.23 mIoU: 74.23
mIoU(ms+flip): 75.79 mIoU(ms+flip): 75.79
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r18b-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_512x1024_80k_cityscapes/pspnet_r18b-d8_512x1024_80k_cityscapes_20201226_063116-26928a60.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_512x1024_80k_cityscapes/pspnet_r18b-d8_512x1024_80k_cityscapes_20201226_063116-26928a60.pth
- Config: configs/pspnet/pspnet_r50b-d8_512x1024_80k_cityscapes.py - Name: pspnet_r50b-d8_512x1024_80k_cityscapes
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-50b-D8 backbone: R-50b-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 232.56
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 232.56
lr schd: 80000
memory (GB): 6.0 memory (GB): 6.0
Name: pspnet_r50b-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.22 mIoU: 78.22
mIoU(ms+flip): 79.46 mIoU(ms+flip): 79.46
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r50b-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_512x1024_80k_cityscapes/pspnet_r50b-d8_512x1024_80k_cityscapes_20201225_094315-6344287a.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_512x1024_80k_cityscapes/pspnet_r50b-d8_512x1024_80k_cityscapes_20201225_094315-6344287a.pth
- Config: configs/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes.py - Name: pspnet_r101b-d8_512x1024_80k_cityscapes
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101b-D8 backbone: R-101b-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 362.32
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 362.32
lr schd: 80000
memory (GB): 9.5 memory (GB): 9.5
Name: pspnet_r101b-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.69 mIoU: 79.69
mIoU(ms+flip): 80.79 mIoU(ms+flip): 80.79
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes_20201226_170012-3a4d38ab.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_512x1024_80k_cityscapes/pspnet_r101b-d8_512x1024_80k_cityscapes_20201226_170012-3a4d38ab.pth
- Config: configs/pspnet/pspnet_r18b-d8_769x769_80k_cityscapes.py - Name: pspnet_r18b-d8_769x769_80k_cityscapes
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-18b-D8 backbone: R-18b-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 156.01
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 156.01
lr schd: 80000
memory (GB): 1.7 memory (GB): 1.7
Name: pspnet_r18b-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 74.92 mIoU: 74.92
mIoU(ms+flip): 76.9 mIoU(ms+flip): 76.9
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r18b-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_769x769_80k_cityscapes/pspnet_r18b-d8_769x769_80k_cityscapes_20201226_080942-bf98d186.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18b-d8_769x769_80k_cityscapes/pspnet_r18b-d8_769x769_80k_cityscapes_20201226_080942-bf98d186.pth
- Config: configs/pspnet/pspnet_r50b-d8_769x769_80k_cityscapes.py - Name: pspnet_r50b-d8_769x769_80k_cityscapes
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-50b-D8 backbone: R-50b-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 531.91
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 531.91
lr schd: 80000
memory (GB): 6.8 memory (GB): 6.8
Name: pspnet_r50b-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.5 mIoU: 78.5
mIoU(ms+flip): 79.96 mIoU(ms+flip): 79.96
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r50b-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_769x769_80k_cityscapes/pspnet_r50b-d8_769x769_80k_cityscapes_20201225_094316-4c643cf6.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50b-d8_769x769_80k_cityscapes/pspnet_r50b-d8_769x769_80k_cityscapes_20201225_094316-4c643cf6.pth
- Config: configs/pspnet/pspnet_r101b-d8_769x769_80k_cityscapes.py - Name: pspnet_r101b-d8_769x769_80k_cityscapes
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101b-D8 backbone: R-101b-D8
crop size: (769,769) crop size: (769,769)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 854.7
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 854.7
lr schd: 80000
memory (GB): 10.8 memory (GB): 10.8
Name: pspnet_r101b-d8_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.87 mIoU: 78.87
mIoU(ms+flip): 80.04 mIoU(ms+flip): 80.04
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101b-d8_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_769x769_80k_cityscapes/pspnet_r101b-d8_769x769_80k_cityscapes_20201226_171823-f0e7c293.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101b-d8_769x769_80k_cityscapes/pspnet_r101b-d8_769x769_80k_cityscapes_20201226_171823-f0e7c293.pth
- Config: configs/pspnet/pspnet_r50-d8_512x512_80k_ade20k.py - Name: pspnet_r50-d8_512x512_80k_ade20k
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 42.5
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 42.5
lr schd: 80000
memory (GB): 8.5 memory (GB): 8.5
Name: pspnet_r50-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 41.13 mIoU: 41.13
mIoU(ms+flip): 41.94 mIoU(ms+flip): 41.94
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r50-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_ade20k/pspnet_r50-d8_512x512_80k_ade20k_20200615_014128-15a8b914.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_80k_ade20k/pspnet_r50-d8_512x512_80k_ade20k_20200615_014128-15a8b914.pth
- Config: configs/pspnet/pspnet_r101-d8_512x512_80k_ade20k.py - Name: pspnet_r101-d8_512x512_80k_ade20k
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 65.36
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 65.36
lr schd: 80000
memory (GB): 12.0 memory (GB): 12.0
Name: pspnet_r101-d8_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 43.57 mIoU: 43.57
mIoU(ms+flip): 44.35 mIoU(ms+flip): 44.35
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101-d8_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_ade20k/pspnet_r101-d8_512x512_80k_ade20k_20200614_031423-b6e782f0.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_80k_ade20k/pspnet_r101-d8_512x512_80k_ade20k_20200614_031423-b6e782f0.pth
- Config: configs/pspnet/pspnet_r50-d8_512x512_160k_ade20k.py - Name: pspnet_r50-d8_512x512_160k_ade20k
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: pspnet_r50-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.48 mIoU: 42.48
mIoU(ms+flip): 43.44 mIoU(ms+flip): 43.44
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r50-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_160k_ade20k/pspnet_r50-d8_512x512_160k_ade20k_20200615_184358-1890b0bd.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_160k_ade20k/pspnet_r50-d8_512x512_160k_ade20k_20200615_184358-1890b0bd.pth
- Config: configs/pspnet/pspnet_r101-d8_512x512_160k_ade20k.py - Name: pspnet_r101-d8_512x512_160k_ade20k
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: pspnet_r101-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 44.39 mIoU: 44.39
mIoU(ms+flip): 45.35 mIoU(ms+flip): 45.35
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_160k_ade20k/pspnet_r101-d8_512x512_160k_ade20k_20200615_100650-967c316f.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_160k_ade20k/pspnet_r101-d8_512x512_160k_ade20k_20200615_100650-967c316f.pth
- Config: configs/pspnet/pspnet_r50-d8_512x512_20k_voc12aug.py - Name: pspnet_r50-d8_512x512_20k_voc12aug
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 42.39
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 42.39
lr schd: 20000
memory (GB): 6.1 memory (GB): 6.1
Name: pspnet_r50-d8_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 76.78 mIoU: 76.78
mIoU(ms+flip): 77.61 mIoU(ms+flip): 77.61
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r50-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_20k_voc12aug/pspnet_r50-d8_512x512_20k_voc12aug_20200617_101958-ed5dfbd9.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_20k_voc12aug/pspnet_r50-d8_512x512_20k_voc12aug_20200617_101958-ed5dfbd9.pth
- Config: configs/pspnet/pspnet_r101-d8_512x512_20k_voc12aug.py - Name: pspnet_r101-d8_512x512_20k_voc12aug
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 66.58
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 66.58
lr schd: 20000
memory (GB): 9.6 memory (GB): 9.6
Name: pspnet_r101-d8_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 78.47 mIoU: 78.47
mIoU(ms+flip): 79.25 mIoU(ms+flip): 79.25
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101-d8_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_20k_voc12aug/pspnet_r101-d8_512x512_20k_voc12aug_20200617_102003-4aef3c9a.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_20k_voc12aug/pspnet_r101-d8_512x512_20k_voc12aug_20200617_102003-4aef3c9a.pth
- Config: configs/pspnet/pspnet_r50-d8_512x512_40k_voc12aug.py - Name: pspnet_r50-d8_512x512_40k_voc12aug
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: pspnet_r50-d8_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 77.29 mIoU: 77.29
mIoU(ms+flip): 78.48 mIoU(ms+flip): 78.48
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r50-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_40k_voc12aug/pspnet_r50-d8_512x512_40k_voc12aug_20200613_161222-ae9c1b8c.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_40k_voc12aug/pspnet_r50-d8_512x512_40k_voc12aug_20200613_161222-ae9c1b8c.pth
- Config: configs/pspnet/pspnet_r101-d8_512x512_40k_voc12aug.py - Name: pspnet_r101-d8_512x512_40k_voc12aug
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: pspnet_r101-d8_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 78.52 mIoU: 78.52
mIoU(ms+flip): 79.57 mIoU(ms+flip): 79.57
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101-d8_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_40k_voc12aug/pspnet_r101-d8_512x512_40k_voc12aug_20200613_161222-bc933b18.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_40k_voc12aug/pspnet_r101-d8_512x512_40k_voc12aug_20200613_161222-bc933b18.pth
- Config: configs/pspnet/pspnet_r101-d8_480x480_40k_pascal_context.py - Name: pspnet_r101-d8_480x480_40k_pascal_context
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (480,480) crop size: (480,480)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 103.31
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (480,480) resolution: (480,480)
value: 103.31
lr schd: 40000
memory (GB): 8.8 memory (GB): 8.8
Name: pspnet_r101-d8_480x480_40k_pascal_context
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal Context Dataset: Pascal Context
Metrics: Metrics:
mIoU: 46.6 mIoU: 46.6
mIoU(ms+flip): 47.78 mIoU(ms+flip): 47.78
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101-d8_480x480_40k_pascal_context.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context/pspnet_r101-d8_480x480_40k_pascal_context_20200911_211210-bf0f5d7c.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context/pspnet_r101-d8_480x480_40k_pascal_context_20200911_211210-bf0f5d7c.pth
- Config: configs/pspnet/pspnet_r101-d8_480x480_80k_pascal_context.py - Name: pspnet_r101-d8_480x480_80k_pascal_context
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (480,480) crop size: (480,480)
lr schd: 80000 lr schd: 80000
Name: pspnet_r101-d8_480x480_80k_pascal_context
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal Context Dataset: Pascal Context
Metrics: Metrics:
mIoU: 46.03 mIoU: 46.03
mIoU(ms+flip): 47.15 mIoU(ms+flip): 47.15
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101-d8_480x480_80k_pascal_context.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context/pspnet_r101-d8_480x480_80k_pascal_context_20200911_190530-c86d6233.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context/pspnet_r101-d8_480x480_80k_pascal_context_20200911_190530-c86d6233.pth
- Config: configs/pspnet/pspnet_r101-d8_480x480_40k_pascal_context_59.py - Name: pspnet_r101-d8_480x480_40k_pascal_context_59
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (480,480) crop size: (480,480)
lr schd: 40000 lr schd: 40000
Name: pspnet_r101-d8_480x480_40k_pascal_context_59
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal Context 59 Dataset: Pascal Context 59
Metrics: Metrics:
mIoU: 52.02 mIoU: 52.02
mIoU(ms+flip): 53.54 mIoU(ms+flip): 53.54
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101-d8_480x480_40k_pascal_context_59.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context_59/pspnet_r101-d8_480x480_40k_pascal_context_59_20210416_114524-86d44cd4.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_40k_pascal_context_59/pspnet_r101-d8_480x480_40k_pascal_context_59_20210416_114524-86d44cd4.pth
- Config: configs/pspnet/pspnet_r101-d8_480x480_80k_pascal_context_59.py - Name: pspnet_r101-d8_480x480_80k_pascal_context_59
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (480,480) crop size: (480,480)
lr schd: 80000 lr schd: 80000
Name: pspnet_r101-d8_480x480_80k_pascal_context_59
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal Context 59 Dataset: Pascal Context 59
Metrics: Metrics:
mIoU: 52.47 mIoU: 52.47
mIoU(ms+flip): 53.99 mIoU(ms+flip): 53.99
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101-d8_480x480_80k_pascal_context_59.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context_59/pspnet_r101-d8_480x480_80k_pascal_context_59_20210416_114418-fa6caaa2.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_480x480_80k_pascal_context_59/pspnet_r101-d8_480x480_80k_pascal_context_59_20210416_114418-fa6caaa2.pth
- Config: configs/pspnet/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k.py - Name: pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 48.78
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 48.78
lr schd: 20000
memory (GB): 9.6 memory (GB): 9.6
Name: pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 10k Dataset: COCO-Stuff 10k
Metrics: Metrics:
mIoU: 35.69 mIoU: 35.69
mIoU(ms+flip): 36.62 mIoU(ms+flip): 36.62
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k_20210820_203258-b88df27f.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_20k_coco-stuff10k_20210820_203258-b88df27f.pth
- Config: configs/pspnet/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k.py - Name: pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 90.09
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 90.09
lr schd: 20000
memory (GB): 13.2 memory (GB): 13.2
Name: pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 10k Dataset: COCO-Stuff 10k
Metrics: Metrics:
mIoU: 37.26 mIoU: 37.26
mIoU(ms+flip): 38.52 mIoU(ms+flip): 38.52
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k_20210820_232135-76aae482.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_20k_coco-stuff10k_20210820_232135-76aae482.pth
- Config: configs/pspnet/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k.py - Name: pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 10k Dataset: COCO-Stuff 10k
Metrics: Metrics:
mIoU: 36.33 mIoU: 36.33
mIoU(ms+flip): 37.24 mIoU(ms+flip): 37.24
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_030857-92e2902b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_030857-92e2902b.pth
- Config: configs/pspnet/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k.py - Name: pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 10k Dataset: COCO-Stuff 10k
Metrics: Metrics:
mIoU: 37.76 mIoU: 37.76
mIoU(ms+flip): 38.86 mIoU(ms+flip): 38.86
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_014022-831aec95.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k/pspnet_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_014022-831aec95.pth
- Config: configs/pspnet/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k.py - Name: pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 48.78
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 48.78
lr schd: 80000
memory (GB): 9.6 memory (GB): 9.6
Name: pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 164k Dataset: COCO-Stuff 164k
Metrics: Metrics:
mIoU: 38.8 mIoU: 38.8
mIoU(ms+flip): 39.19 mIoU(ms+flip): 39.19
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034-0e41b2db.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034-0e41b2db.pth
- Config: configs/pspnet/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k.py - Name: pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 90.09
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 90.09
lr schd: 80000
memory (GB): 13.2 memory (GB): 13.2
Name: pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 164k Dataset: COCO-Stuff 164k
Metrics: Metrics:
mIoU: 40.34 mIoU: 40.34
mIoU(ms+flip): 40.79 mIoU(ms+flip): 40.79
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034-7eb41789.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_80k_coco-stuff164k_20210707_152034-7eb41789.pth
- Config: configs/pspnet/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k.py - Name: pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 164k Dataset: COCO-Stuff 164k
Metrics: Metrics:
mIoU: 39.64 mIoU: 39.64
mIoU(ms+flip): 39.97 mIoU(ms+flip): 39.97
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004-51276a57.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004-51276a57.pth
- Config: configs/pspnet/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k.py - Name: pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 164k Dataset: COCO-Stuff 164k
Metrics: Metrics:
mIoU: 41.28 mIoU: 41.28
mIoU(ms+flip): 41.66 mIoU(ms+flip): 41.66
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004-4af9621b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_160k_coco-stuff164k_20210707_152004-4af9621b.pth
- Config: configs/pspnet/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k.py - Name: pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-50-D8 backbone: R-50-D8
crop size: (512,512) crop size: (512,512)
lr schd: 320000 lr schd: 320000
Name: pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 164k Dataset: COCO-Stuff 164k
Metrics: Metrics:
mIoU: 40.53 mIoU: 40.53
mIoU(ms+flip): 40.75 mIoU(ms+flip): 40.75
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004-be9610cc.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004-be9610cc.pth
- Config: configs/pspnet/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k.py - Name: pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k
In Collection: pspnet In Collection: pspnet
Metadata: Metadata:
backbone: R-101-D8 backbone: R-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 320000 lr schd: 320000
Name: pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k
Results: Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 164k Dataset: COCO-Stuff 164k
Metrics: Metrics:
mIoU: 41.95 mIoU: 41.95
mIoU(ms+flip): 42.42 mIoU(ms+flip): 42.42
Task: Semantic Segmentation Config: configs/pspnet/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004-72220c60.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004-72220c60.pth

9
configs/resnest/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/zhanghang1989/ResNeSt">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/resnest.py#L271">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/2004.08955">ResNeSt (ArXiv'2020)</a></summary>
```latex ```latex
@article{zhang2020resnest, @article{zhang2020resnest,
title={ResNeSt: Split-Attention Networks}, title={ResNeSt: Split-Attention Networks},
@ -13,6 +20,8 @@ year={2020}
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

125
configs/resnest/resnest.yml
View File

@ -1,183 +1,192 @@
Collections: Collections:
- Metadata: - Name: resnest
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20k - ADE20k
Name: resnest Paper:
URL: https://arxiv.org/abs/2004.08955
Title: 'ResNeSt: Split-Attention Networks'
README: configs/resnest/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/resnest.py#L271
Version: v0.17.0
Converted From:
Code: https://github.com/zhanghang1989/ResNeSt
Models: Models:
- Config: configs/resnest/fcn_s101-d8_512x1024_80k_cityscapes.py - Name: fcn_s101-d8_512x1024_80k_cityscapes
In Collection: resnest In Collection: resnest
Metadata: Metadata:
backbone: S-101-D8 backbone: S-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 418.41
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 418.41
lr schd: 80000
memory (GB): 11.4 memory (GB): 11.4
Name: fcn_s101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.56 mIoU: 77.56
mIoU(ms+flip): 78.98 mIoU(ms+flip): 78.98
Task: Semantic Segmentation Config: configs/resnest/fcn_s101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x1024_80k_cityscapes/fcn_s101-d8_512x1024_80k_cityscapes_20200807_140631-f8d155b3.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x1024_80k_cityscapes/fcn_s101-d8_512x1024_80k_cityscapes_20200807_140631-f8d155b3.pth
- Config: configs/resnest/pspnet_s101-d8_512x1024_80k_cityscapes.py - Name: pspnet_s101-d8_512x1024_80k_cityscapes
In Collection: resnest In Collection: resnest
Metadata: Metadata:
backbone: S-101-D8 backbone: S-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 396.83
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 396.83
lr schd: 80000
memory (GB): 11.8 memory (GB): 11.8
Name: pspnet_s101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.57 mIoU: 78.57
mIoU(ms+flip): 79.19 mIoU(ms+flip): 79.19
Task: Semantic Segmentation Config: configs/resnest/pspnet_s101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x1024_80k_cityscapes/pspnet_s101-d8_512x1024_80k_cityscapes_20200807_140631-c75f3b99.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x1024_80k_cityscapes/pspnet_s101-d8_512x1024_80k_cityscapes_20200807_140631-c75f3b99.pth
- Config: configs/resnest/deeplabv3_s101-d8_512x1024_80k_cityscapes.py - Name: deeplabv3_s101-d8_512x1024_80k_cityscapes
In Collection: resnest In Collection: resnest
Metadata: Metadata:
backbone: S-101-D8 backbone: S-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 531.91
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 531.91
lr schd: 80000
memory (GB): 11.9 memory (GB): 11.9
Name: deeplabv3_s101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.67 mIoU: 79.67
mIoU(ms+flip): 80.51 mIoU(ms+flip): 80.51
Task: Semantic Segmentation Config: configs/resnest/deeplabv3_s101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x1024_80k_cityscapes/deeplabv3_s101-d8_512x1024_80k_cityscapes_20200807_144429-b73c4270.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x1024_80k_cityscapes/deeplabv3_s101-d8_512x1024_80k_cityscapes_20200807_144429-b73c4270.pth
- Config: configs/resnest/deeplabv3plus_s101-d8_512x1024_80k_cityscapes.py - Name: deeplabv3plus_s101-d8_512x1024_80k_cityscapes
In Collection: resnest In Collection: resnest
Metadata: Metadata:
backbone: S-101-D8 backbone: S-101-D8
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 423.73
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 423.73
lr schd: 80000
memory (GB): 13.2 memory (GB): 13.2
Name: deeplabv3plus_s101-d8_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.62 mIoU: 79.62
mIoU(ms+flip): 80.27 mIoU(ms+flip): 80.27
Task: Semantic Segmentation Config: configs/resnest/deeplabv3plus_s101-d8_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x1024_80k_cityscapes/deeplabv3plus_s101-d8_512x1024_80k_cityscapes_20200807_144429-1239eb43.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x1024_80k_cityscapes/deeplabv3plus_s101-d8_512x1024_80k_cityscapes_20200807_144429-1239eb43.pth
- Config: configs/resnest/fcn_s101-d8_512x512_160k_ade20k.py - Name: fcn_s101-d8_512x512_160k_ade20k
In Collection: resnest In Collection: resnest
Metadata: Metadata:
backbone: S-101-D8 backbone: S-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 77.76
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 77.76
lr schd: 160000
memory (GB): 14.2 memory (GB): 14.2
Name: fcn_s101-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20k Dataset: ADE20k
Metrics: Metrics:
mIoU: 45.62 mIoU: 45.62
mIoU(ms+flip): 46.16 mIoU(ms+flip): 46.16
Task: Semantic Segmentation Config: configs/resnest/fcn_s101-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x512_160k_ade20k/fcn_s101-d8_512x512_160k_ade20k_20200807_145416-d3160329.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/fcn_s101-d8_512x512_160k_ade20k/fcn_s101-d8_512x512_160k_ade20k_20200807_145416-d3160329.pth
- Config: configs/resnest/pspnet_s101-d8_512x512_160k_ade20k.py - Name: pspnet_s101-d8_512x512_160k_ade20k
In Collection: resnest In Collection: resnest
Metadata: Metadata:
backbone: S-101-D8 backbone: S-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 76.8
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 76.8
lr schd: 160000
memory (GB): 14.2 memory (GB): 14.2
Name: pspnet_s101-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20k Dataset: ADE20k
Metrics: Metrics:
mIoU: 45.44 mIoU: 45.44
mIoU(ms+flip): 46.28 mIoU(ms+flip): 46.28
Task: Semantic Segmentation Config: configs/resnest/pspnet_s101-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x512_160k_ade20k/pspnet_s101-d8_512x512_160k_ade20k_20200807_145416-a6daa92a.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/pspnet_s101-d8_512x512_160k_ade20k/pspnet_s101-d8_512x512_160k_ade20k_20200807_145416-a6daa92a.pth
- Config: configs/resnest/deeplabv3_s101-d8_512x512_160k_ade20k.py - Name: deeplabv3_s101-d8_512x512_160k_ade20k
In Collection: resnest In Collection: resnest
Metadata: Metadata:
backbone: S-101-D8 backbone: S-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 107.76
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 107.76
lr schd: 160000
memory (GB): 14.6 memory (GB): 14.6
Name: deeplabv3_s101-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20k Dataset: ADE20k
Metrics: Metrics:
mIoU: 45.71 mIoU: 45.71
mIoU(ms+flip): 46.59 mIoU(ms+flip): 46.59
Task: Semantic Segmentation Config: configs/resnest/deeplabv3_s101-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x512_160k_ade20k/deeplabv3_s101-d8_512x512_160k_ade20k_20200807_144503-17ecabe5.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x512_160k_ade20k/deeplabv3_s101-d8_512x512_160k_ade20k_20200807_144503-17ecabe5.pth
- Config: configs/resnest/deeplabv3plus_s101-d8_512x512_160k_ade20k.py - Name: deeplabv3plus_s101-d8_512x512_160k_ade20k
In Collection: resnest In Collection: resnest
Metadata: Metadata:
backbone: S-101-D8 backbone: S-101-D8
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 83.61
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 83.61
lr schd: 160000
memory (GB): 16.2 memory (GB): 16.2
Name: deeplabv3plus_s101-d8_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20k Dataset: ADE20k
Metrics: Metrics:
mIoU: 46.47 mIoU: 46.47
mIoU(ms+flip): 47.27 mIoU(ms+flip): 47.27
Task: Semantic Segmentation Config: configs/resnest/deeplabv3plus_s101-d8_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x512_160k_ade20k/deeplabv3plus_s101-d8_512x512_160k_ade20k_20200807_144503-27b26226.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x512_160k_ade20k/deeplabv3plus_s101-d8_512x512_160k_ade20k_20200807_144503-27b26226.pth

9
configs/segformer/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/NVlabs/SegFormer">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mit.py#L246">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/2105.15203">SegFormer (ArXiv'2021)</a></summary>
```latex ```latex
@article{xie2021segformer, @article{xie2021segformer,
title={SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers}, title={SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers},
@ -13,6 +20,8 @@
} }
``` ```
</details>
## Usage ## Usage
To use other repositories' pre-trained models, it is necessary to convert keys. To use other repositories' pre-trained models, it is necessary to convert keys.

111
configs/segformer/segformer.yml
View File

@ -1,160 +1,169 @@
Collections: Collections:
- Metadata: - Name: segformer
Metadata:
Training Data: Training Data:
- ADE20k - ADE20k
Name: segformer Paper:
URL: https://arxiv.org/abs/2105.15203
Title: resize image to multiple of 32, improve SegFormer by 0.5-1.0 mIoU.
README: configs/segformer/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mit.py#L246
Version: v0.17.0
Converted From:
Code: https://github.com/NVlabs/SegFormer
Models: Models:
- Config: configs/segformer/segformer_mit-b0_512x512_160k_ade20k.py - Name: segformer_mit-b0_512x512_160k_ade20k
In Collection: segformer In Collection: segformer
Metadata: Metadata:
backbone: MIT-B0 backbone: MIT-B0
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 19.49
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 19.49
lr schd: 160000
memory (GB): 2.1 memory (GB): 2.1
Name: segformer_mit-b0_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20k Dataset: ADE20k
Metrics: Metrics:
mIoU: 37.41 mIoU: 37.41
mIoU(ms+flip): 38.34 mIoU(ms+flip): 38.34
Task: Semantic Segmentation Config: configs/segformer/segformer_mit-b0_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_512x512_160k_ade20k/segformer_mit-b0_512x512_160k_ade20k_20210726_101530-8ffa8fda.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_512x512_160k_ade20k/segformer_mit-b0_512x512_160k_ade20k_20210726_101530-8ffa8fda.pth
- Config: configs/segformer/segformer_mit-b1_512x512_160k_ade20k.py - Name: segformer_mit-b1_512x512_160k_ade20k
In Collection: segformer In Collection: segformer
Metadata: Metadata:
backbone: MIT-B1 backbone: MIT-B1
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 20.98
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 20.98
lr schd: 160000
memory (GB): 2.6 memory (GB): 2.6
Name: segformer_mit-b1_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20k Dataset: ADE20k
Metrics: Metrics:
mIoU: 40.97 mIoU: 40.97
mIoU(ms+flip): 42.54 mIoU(ms+flip): 42.54
Task: Semantic Segmentation Config: configs/segformer/segformer_mit-b1_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_512x512_160k_ade20k/segformer_mit-b1_512x512_160k_ade20k_20210726_112106-d70e859d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_512x512_160k_ade20k/segformer_mit-b1_512x512_160k_ade20k_20210726_112106-d70e859d.pth
- Config: configs/segformer/segformer_mit-b2_512x512_160k_ade20k.py - Name: segformer_mit-b2_512x512_160k_ade20k
In Collection: segformer In Collection: segformer
Metadata: Metadata:
backbone: MIT-B2 backbone: MIT-B2
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 32.38
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 32.38
lr schd: 160000
memory (GB): 3.6 memory (GB): 3.6
Name: segformer_mit-b2_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20k Dataset: ADE20k
Metrics: Metrics:
mIoU: 45.58 mIoU: 45.58
mIoU(ms+flip): 47.03 mIoU(ms+flip): 47.03
Task: Semantic Segmentation Config: configs/segformer/segformer_mit-b2_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_512x512_160k_ade20k/segformer_mit-b2_512x512_160k_ade20k_20210726_112103-cbd414ac.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_512x512_160k_ade20k/segformer_mit-b2_512x512_160k_ade20k_20210726_112103-cbd414ac.pth
- Config: configs/segformer/segformer_mit-b3_512x512_160k_ade20k.py - Name: segformer_mit-b3_512x512_160k_ade20k
In Collection: segformer In Collection: segformer
Metadata: Metadata:
backbone: MIT-B3 backbone: MIT-B3
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 45.23
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 45.23
lr schd: 160000
memory (GB): 4.8 memory (GB): 4.8
Name: segformer_mit-b3_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20k Dataset: ADE20k
Metrics: Metrics:
mIoU: 47.82 mIoU: 47.82
mIoU(ms+flip): 48.81 mIoU(ms+flip): 48.81
Task: Semantic Segmentation Config: configs/segformer/segformer_mit-b3_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_512x512_160k_ade20k/segformer_mit-b3_512x512_160k_ade20k_20210726_081410-962b98d2.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_512x512_160k_ade20k/segformer_mit-b3_512x512_160k_ade20k_20210726_081410-962b98d2.pth
- Config: configs/segformer/segformer_mit-b4_512x512_160k_ade20k.py - Name: segformer_mit-b4_512x512_160k_ade20k
In Collection: segformer In Collection: segformer
Metadata: Metadata:
backbone: MIT-B4 backbone: MIT-B4
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 64.72
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 64.72
lr schd: 160000
memory (GB): 6.1 memory (GB): 6.1
Name: segformer_mit-b4_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20k Dataset: ADE20k
Metrics: Metrics:
mIoU: 48.46 mIoU: 48.46
mIoU(ms+flip): 49.76 mIoU(ms+flip): 49.76
Task: Semantic Segmentation Config: configs/segformer/segformer_mit-b4_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_512x512_160k_ade20k/segformer_mit-b4_512x512_160k_ade20k_20210728_183055-7f509d7d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_512x512_160k_ade20k/segformer_mit-b4_512x512_160k_ade20k_20210728_183055-7f509d7d.pth
- Config: configs/segformer/segformer_mit-b5_512x512_160k_ade20k.py - Name: segformer_mit-b5_512x512_160k_ade20k
In Collection: segformer In Collection: segformer
Metadata: Metadata:
backbone: MIT-B5 backbone: MIT-B5
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 84.1
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 84.1
lr schd: 160000
memory (GB): 7.2 memory (GB): 7.2
Name: segformer_mit-b5_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20k Dataset: ADE20k
Metrics: Metrics:
mIoU: 49.13 mIoU: 49.13
mIoU(ms+flip): 50.22 mIoU(ms+flip): 50.22
Task: Semantic Segmentation Config: configs/segformer/segformer_mit-b5_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_512x512_160k_ade20k/segformer_mit-b5_512x512_160k_ade20k_20210726_145235-94cedf59.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_512x512_160k_ade20k/segformer_mit-b5_512x512_160k_ade20k_20210726_145235-94cedf59.pth
- Config: configs/segformer/segformer_mit-b5_640x640_160k_ade20k.py - Name: segformer_mit-b5_640x640_160k_ade20k
In Collection: segformer In Collection: segformer
Metadata: Metadata:
backbone: MIT-B5 backbone: MIT-B5
crop size: (640,640) crop size: (640,640)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 88.5
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (640,640) resolution: (640,640)
value: 88.5
lr schd: 160000
memory (GB): 11.5 memory (GB): 11.5
Name: segformer_mit-b5_640x640_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20k Dataset: ADE20k
Metrics: Metrics:
mIoU: 49.62 mIoU: 49.62
mIoU(ms+flip): 50.36 mIoU(ms+flip): 50.36
Task: Semantic Segmentation Config: configs/segformer/segformer_mit-b5_640x640_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_640x640_160k_ade20k/segformer_mit-b5_640x640_160k_ade20k_20210801_121243-41d2845b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_640x640_160k_ade20k/segformer_mit-b5_640x640_160k_ade20k_20210801_121243-41d2845b.pth

9
configs/sem_fpn/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/facebookresearch/detectron2">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fpn_head.py#L12">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1901.02446">Semantic FPN (CVPR'2019)</a></summary>
```latex ```latex
@article{Kirillov_2019, @article{Kirillov_2019,
title={Panoptic Feature Pyramid Networks}, title={Panoptic Feature Pyramid Networks},
@ -18,6 +25,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

69
configs/sem_fpn/sem_fpn.yml
View File

@ -1,95 +1,104 @@
Collections: Collections:
- Metadata: - Name: sem_fpn
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20K - ADE20K
Name: sem_fpn Paper:
URL: https://arxiv.org/abs/1901.02446
Title: Panoptic Feature Pyramid Networks
README: configs/sem_fpn/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fpn_head.py#L12
Version: v0.17.0
Converted From:
Code: https://github.com/facebookresearch/detectron2
Models: Models:
- Config: configs/sem_fpn/fpn_r50_512x1024_80k_cityscapes.py - Name: fpn_r50_512x1024_80k_cityscapes
In Collection: sem_fpn In Collection: sem_fpn
Metadata: Metadata:
backbone: R-50 backbone: R-50
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 73.86
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 73.86
lr schd: 80000
memory (GB): 2.8 memory (GB): 2.8
Name: fpn_r50_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 74.52 mIoU: 74.52
mIoU(ms+flip): 76.08 mIoU(ms+flip): 76.08
Task: Semantic Segmentation Config: configs/sem_fpn/fpn_r50_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x1024_80k_cityscapes/fpn_r50_512x1024_80k_cityscapes_20200717_021437-94018a0d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x1024_80k_cityscapes/fpn_r50_512x1024_80k_cityscapes_20200717_021437-94018a0d.pth
- Config: configs/sem_fpn/fpn_r101_512x1024_80k_cityscapes.py - Name: fpn_r101_512x1024_80k_cityscapes
In Collection: sem_fpn In Collection: sem_fpn
Metadata: Metadata:
backbone: R-101 backbone: R-101
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 97.18
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 97.18
lr schd: 80000
memory (GB): 3.9 memory (GB): 3.9
Name: fpn_r101_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 75.8 mIoU: 75.8
mIoU(ms+flip): 77.4 mIoU(ms+flip): 77.4
Task: Semantic Segmentation Config: configs/sem_fpn/fpn_r101_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x1024_80k_cityscapes/fpn_r101_512x1024_80k_cityscapes_20200717_012416-c5800d4c.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x1024_80k_cityscapes/fpn_r101_512x1024_80k_cityscapes_20200717_012416-c5800d4c.pth
- Config: configs/sem_fpn/fpn_r50_512x512_160k_ade20k.py - Name: fpn_r50_512x512_160k_ade20k
In Collection: sem_fpn In Collection: sem_fpn
Metadata: Metadata:
backbone: R-50 backbone: R-50
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 17.93
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 17.93
lr schd: 160000
memory (GB): 4.9 memory (GB): 4.9
Name: fpn_r50_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 37.49 mIoU: 37.49
mIoU(ms+flip): 39.09 mIoU(ms+flip): 39.09
Task: Semantic Segmentation Config: configs/sem_fpn/fpn_r50_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x512_160k_ade20k/fpn_r50_512x512_160k_ade20k_20200718_131734-5b5a6ab9.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r50_512x512_160k_ade20k/fpn_r50_512x512_160k_ade20k_20200718_131734-5b5a6ab9.pth
- Config: configs/sem_fpn/fpn_r101_512x512_160k_ade20k.py - Name: fpn_r101_512x512_160k_ade20k
In Collection: sem_fpn In Collection: sem_fpn
Metadata: Metadata:
backbone: R-101 backbone: R-101
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 24.64
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 24.64
lr schd: 160000
memory (GB): 5.9 memory (GB): 5.9
Name: fpn_r101_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 39.35 mIoU: 39.35
mIoU(ms+flip): 40.72 mIoU(ms+flip): 40.72
Task: Semantic Segmentation Config: configs/sem_fpn/fpn_r101_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x512_160k_ade20k/fpn_r101_512x512_160k_ade20k_20200718_131734-306b5004.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/sem_fpn/fpn_r101_512x512_160k_ade20k/fpn_r101_512x512_160k_ade20k_20200718_131734-306b5004.pth

13
configs/setr/README.md
View File

@ -4,6 +4,17 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/fudan-zvg/SETR">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/setr_up_head.py#L11">Code Snippet</a>
```None
This head has two version head.
```
<details>
<summary align="right"><a href="https://arxiv.org/abs/2012.15840">SETR (CVPR'2021)</a></summary>
```latex ```latex
@article{zheng2020rethinking, @article{zheng2020rethinking,
title={Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers}, title={Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers},
@ -13,6 +24,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### ADE20K ### ADE20K

62
configs/setr/setr.yml
View File

@ -1,87 +1,97 @@
Collections: Collections:
- Metadata: - Name: setr
Metadata:
Training Data: Training Data:
- ADE20K - ADE20K
Name: setr Paper:
URL: https://arxiv.org/abs/2012.15840
Title: Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective
with Transformers
README: configs/setr/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/setr_up_head.py#L11
Version: v0.17.0
Converted From:
Code: https://github.com/fudan-zvg/SETR
Models: Models:
- Config: configs/setr/setr_naive_512x512_160k_b16_ade20k.py - Name: setr_naive_512x512_160k_b16_ade20k
In Collection: setr In Collection: setr
Metadata: Metadata:
backbone: ViT-L backbone: ViT-L
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 211.86
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 211.86
lr schd: 160000
memory (GB): 18.4 memory (GB): 18.4
Name: setr_naive_512x512_160k_b16_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 48.28 mIoU: 48.28
mIoU(ms+flip): 49.56 mIoU(ms+flip): 49.56
Task: Semantic Segmentation Config: configs/setr/setr_naive_512x512_160k_b16_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_512x512_160k_b16_ade20k/setr_naive_512x512_160k_b16_ade20k_20210619_191258-061f24f5.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_naive_512x512_160k_b16_ade20k/setr_naive_512x512_160k_b16_ade20k_20210619_191258-061f24f5.pth
- Config: configs/setr/setr_pup_512x512_160k_b16_ade20k.py - Name: setr_pup_512x512_160k_b16_ade20k
In Collection: setr In Collection: setr
Metadata: Metadata:
backbone: ViT-L backbone: ViT-L
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 222.22
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 222.22
lr schd: 160000
memory (GB): 19.54 memory (GB): 19.54
Name: setr_pup_512x512_160k_b16_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 48.24 mIoU: 48.24
mIoU(ms+flip): 49.99 mIoU(ms+flip): 49.99
Task: Semantic Segmentation Config: configs/setr/setr_pup_512x512_160k_b16_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_512x512_160k_b16_ade20k/setr_pup_512x512_160k_b16_ade20k_20210619_191343-7e0ce826.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_pup_512x512_160k_b16_ade20k/setr_pup_512x512_160k_b16_ade20k_20210619_191343-7e0ce826.pth
- Config: configs/setr/setr_mla_512x512_160k_b8_ade20k.py - Name: setr_mla_512x512_160k_b8_ade20k
In Collection: setr In Collection: setr
Metadata: Metadata:
backbone: ViT-L backbone: ViT-L
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
memory (GB): 10.96 memory (GB): 10.96
Name: setr_mla_512x512_160k_b8_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 47.34 mIoU: 47.34
mIoU(ms+flip): 49.05 mIoU(ms+flip): 49.05
Task: Semantic Segmentation Config: configs/setr/setr_mla_512x512_160k_b8_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b8_ade20k/setr_mla_512x512_160k_b8_ade20k_20210619_191118-c6d21df0.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b8_ade20k/setr_mla_512x512_160k_b8_ade20k_20210619_191118-c6d21df0.pth
- Config: configs/setr/setr_mla_512x512_160k_b16_ade20k.py - Name: setr_mla_512x512_160k_b16_ade20k
In Collection: setr In Collection: setr
Metadata: Metadata:
backbone: ViT-L backbone: ViT-L
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 190.48
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 190.48
lr schd: 160000
memory (GB): 17.3 memory (GB): 17.3
Name: setr_mla_512x512_160k_b16_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 47.54 mIoU: 47.54
mIoU(ms+flip): 49.37 mIoU(ms+flip): 49.37
Task: Semantic Segmentation Config: configs/setr/setr_mla_512x512_160k_b16_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b16_ade20k/setr_mla_512x512_160k_b16_ade20k_20210619_191057-f9741de7.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/setr/setr_mla_512x512_160k_b16_ade20k/setr_mla_512x512_160k_b16_ade20k_20210619_191057-f9741de7.pth

9
configs/swin/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/microsoft/Swin-Transformer">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/swin.py#L524">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/2103.14030">Swin Transformer (arXiv'2021)</a></summary>
```latex ```latex
@article{liu2021Swin, @article{liu2021Swin,
title={Swin Transformer: Hierarchical Vision Transformer using Shifted Windows}, title={Swin Transformer: Hierarchical Vision Transformer using Shifted Windows},
@ -13,6 +20,8 @@
} }
``` ```
</details>
## Usage ## Usage
To use other repositories' pre-trained models, it is necessary to convert keys. To use other repositories' pre-trained models, it is necessary to convert keys.

81
configs/swin/swin.yml
View File

@ -1,122 +1,131 @@
Collections: Collections:
- Metadata: - Name: swin
Metadata:
Training Data: Training Data:
- ADE20K - ADE20K
Name: swin Paper:
URL: https://arxiv.org/abs/2103.14030
Title: 'Swin Transformer: Hierarchical Vision Transformer using Shifted Windows'
README: configs/swin/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/swin.py#L524
Version: v0.17.0
Converted From:
Code: https://github.com/microsoft/Swin-Transformer
Models: Models:
- Config: configs/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py - Name: upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K
In Collection: swin In Collection: swin
Metadata: Metadata:
backbone: Swin-T backbone: Swin-T
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 47.48
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 47.48
lr schd: 160000
memory (GB): 5.02 memory (GB): 5.02
Name: upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 44.41 mIoU: 44.41
mIoU(ms+flip): 45.79 mIoU(ms+flip): 45.79
Task: Semantic Segmentation Config: configs/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210531_112542-e380ad3e.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210531_112542-e380ad3e.pth
- Config: configs/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py - Name: upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K
In Collection: swin In Collection: swin
Metadata: Metadata:
backbone: Swin-S backbone: Swin-S
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 67.93
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 67.93
lr schd: 160000
memory (GB): 6.17 memory (GB): 6.17
Name: upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 47.72 mIoU: 47.72
mIoU(ms+flip): 49.24 mIoU(ms+flip): 49.24
Task: Semantic Segmentation Config: configs/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192015-ee2fff1c.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192015-ee2fff1c.pth
- Config: configs/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py - Name: upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K
In Collection: swin In Collection: swin
Metadata: Metadata:
backbone: Swin-B backbone: Swin-B
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 79.05
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 79.05
lr schd: 160000
memory (GB): 7.61 memory (GB): 7.61
Name: upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 47.99 mIoU: 47.99
mIoU(ms+flip): 49.57 mIoU(ms+flip): 49.57
Task: Semantic Segmentation Config: configs/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192340-593b0e13.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192340-593b0e13.pth
- Config: configs/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K.py - Name: upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K
In Collection: swin In Collection: swin
Metadata: Metadata:
backbone: Swin-B backbone: Swin-B
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 50.31 mIoU: 50.31
mIoU(ms+flip): 51.9 mIoU(ms+flip): 51.9
Task: Semantic Segmentation Config: configs/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K_20210526_211650-762e2178.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K_20210526_211650-762e2178.pth
- Config: configs/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K.py - Name: upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K
In Collection: swin In Collection: swin
Metadata: Metadata:
backbone: Swin-B backbone: Swin-B
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 82.64
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 82.64
lr schd: 160000
memory (GB): 8.52 memory (GB): 8.52
Name: upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 48.35 mIoU: 48.35
mIoU(ms+flip): 49.65 mIoU(ms+flip): 49.65
Task: Semantic Segmentation Config: configs/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K_20210531_132020-05b22ea4.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K_20210531_132020-05b22ea4.pth
- Config: configs/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K.py - Name: upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K
In Collection: swin In Collection: swin
Metadata: Metadata:
backbone: Swin-B backbone: Swin-B
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 50.76 mIoU: 50.76
mIoU(ms+flip): 52.4 mIoU(ms+flip): 52.4
Task: Semantic Segmentation Config: configs/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K_20210531_125459-429057bf.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K_20210531_125459-429057bf.pth

9
configs/unet/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/abs/1505.04597">UNet (MICCAI'2016/Nat. Methods'2019)</a></summary>
```latex ```latex
@inproceedings{ronneberger2015u, @inproceedings{ronneberger2015u,
title={U-net: Convolutional networks for biomedical image segmentation}, title={U-net: Convolutional networks for biomedical image segmentation},
@ -15,6 +22,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### DRIVE ### DRIVE

85
configs/unet/unet.yml
View File

@ -1,177 +1,186 @@
Collections: Collections:
- Metadata: - Name: unet
Metadata:
Training Data: Training Data:
- DRIVE - DRIVE
- STARE - STARE
- CHASE_DB1 - CHASE_DB1
- HRF - HRF
Name: unet Paper:
URL: https://arxiv.org/abs/1505.04597
Title: 'U-Net: Convolutional Networks for Biomedical Image Segmentation'
README: configs/unet/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225
Version: v0.17.0
Converted From:
Code: http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net
Models: Models:
- Config: configs/unet/fcn_unet_s5-d16_64x64_40k_drive.py - Name: fcn_unet_s5-d16_64x64_40k_drive
In Collection: unet In Collection: unet
Metadata: Metadata:
backbone: UNet-S5-D16 backbone: UNet-S5-D16
crop size: (64,64) crop size: (64,64)
lr schd: 40000 lr schd: 40000
memory (GB): 0.68 memory (GB): 0.68
Name: fcn_unet_s5-d16_64x64_40k_drive
Results: Results:
- Task: Semantic Segmentation
Dataset: DRIVE Dataset: DRIVE
Metrics: Metrics:
mIoU: 78.67 mIoU: 78.67
Task: Semantic Segmentation Config: configs/unet/fcn_unet_s5-d16_64x64_40k_drive.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_64x64_40k_drive/fcn_unet_s5-d16_64x64_40k_drive_20201223_191051-5daf6d3b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_64x64_40k_drive/fcn_unet_s5-d16_64x64_40k_drive_20201223_191051-5daf6d3b.pth
- Config: configs/unet/pspnet_unet_s5-d16_64x64_40k_drive.py - Name: pspnet_unet_s5-d16_64x64_40k_drive
In Collection: unet In Collection: unet
Metadata: Metadata:
backbone: UNet-S5-D16 backbone: UNet-S5-D16
crop size: (64,64) crop size: (64,64)
lr schd: 40000 lr schd: 40000
memory (GB): 0.599 memory (GB): 0.599
Name: pspnet_unet_s5-d16_64x64_40k_drive
Results: Results:
- Task: Semantic Segmentation
Dataset: DRIVE Dataset: DRIVE
Metrics: Metrics:
mIoU: 78.62 mIoU: 78.62
Task: Semantic Segmentation Config: configs/unet/pspnet_unet_s5-d16_64x64_40k_drive.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_64x64_40k_drive/pspnet_unet_s5-d16_64x64_40k_drive_20201227_181818-aac73387.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_64x64_40k_drive/pspnet_unet_s5-d16_64x64_40k_drive_20201227_181818-aac73387.pth
- Config: configs/unet/deeplabv3_unet_s5-d16_64x64_40k_drive.py - Name: deeplabv3_unet_s5-d16_64x64_40k_drive
In Collection: unet In Collection: unet
Metadata: Metadata:
backbone: UNet-S5-D16 backbone: UNet-S5-D16
crop size: (64,64) crop size: (64,64)
lr schd: 40000 lr schd: 40000
memory (GB): 0.596 memory (GB): 0.596
Name: deeplabv3_unet_s5-d16_64x64_40k_drive
Results: Results:
- Task: Semantic Segmentation
Dataset: DRIVE Dataset: DRIVE
Metrics: Metrics:
mIoU: 78.69 mIoU: 78.69
Task: Semantic Segmentation Config: configs/unet/deeplabv3_unet_s5-d16_64x64_40k_drive.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_64x64_40k_drive/deeplabv3_unet_s5-d16_64x64_40k_drive_20201226_094047-0671ff20.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_64x64_40k_drive/deeplabv3_unet_s5-d16_64x64_40k_drive_20201226_094047-0671ff20.pth
- Config: configs/unet/fcn_unet_s5-d16_128x128_40k_stare.py - Name: fcn_unet_s5-d16_128x128_40k_stare
In Collection: unet In Collection: unet
Metadata: Metadata:
backbone: UNet-S5-D16 backbone: UNet-S5-D16
crop size: (128,128) crop size: (128,128)
lr schd: 40000 lr schd: 40000
memory (GB): 0.968 memory (GB): 0.968
Name: fcn_unet_s5-d16_128x128_40k_stare
Results: Results:
- Task: Semantic Segmentation
Dataset: STARE Dataset: STARE
Metrics: Metrics:
mIoU: 81.02 mIoU: 81.02
Task: Semantic Segmentation Config: configs/unet/fcn_unet_s5-d16_128x128_40k_stare.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_stare/fcn_unet_s5-d16_128x128_40k_stare_20201223_191051-7d77e78b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_stare/fcn_unet_s5-d16_128x128_40k_stare_20201223_191051-7d77e78b.pth
- Config: configs/unet/pspnet_unet_s5-d16_128x128_40k_stare.py - Name: pspnet_unet_s5-d16_128x128_40k_stare
In Collection: unet In Collection: unet
Metadata: Metadata:
backbone: UNet-S5-D16 backbone: UNet-S5-D16
crop size: (128,128) crop size: (128,128)
lr schd: 40000 lr schd: 40000
memory (GB): 0.982 memory (GB): 0.982
Name: pspnet_unet_s5-d16_128x128_40k_stare
Results: Results:
- Task: Semantic Segmentation
Dataset: STARE Dataset: STARE
Metrics: Metrics:
mIoU: 81.22 mIoU: 81.22
Task: Semantic Segmentation Config: configs/unet/pspnet_unet_s5-d16_128x128_40k_stare.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_stare/pspnet_unet_s5-d16_128x128_40k_stare_20201227_181818-3c2923c4.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_stare/pspnet_unet_s5-d16_128x128_40k_stare_20201227_181818-3c2923c4.pth
- Config: configs/unet/deeplabv3_unet_s5-d16_128x128_40k_stare.py - Name: deeplabv3_unet_s5-d16_128x128_40k_stare
In Collection: unet In Collection: unet
Metadata: Metadata:
backbone: UNet-S5-D16 backbone: UNet-S5-D16
crop size: (128,128) crop size: (128,128)
lr schd: 40000 lr schd: 40000
memory (GB): 0.999 memory (GB): 0.999
Name: deeplabv3_unet_s5-d16_128x128_40k_stare
Results: Results:
- Task: Semantic Segmentation
Dataset: STARE Dataset: STARE
Metrics: Metrics:
mIoU: 80.93 mIoU: 80.93
Task: Semantic Segmentation Config: configs/unet/deeplabv3_unet_s5-d16_128x128_40k_stare.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_stare/deeplabv3_unet_s5-d16_128x128_40k_stare_20201226_094047-93dcb93c.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_stare/deeplabv3_unet_s5-d16_128x128_40k_stare_20201226_094047-93dcb93c.pth
- Config: configs/unet/fcn_unet_s5-d16_128x128_40k_chase_db1.py - Name: fcn_unet_s5-d16_128x128_40k_chase_db1
In Collection: unet In Collection: unet
Metadata: Metadata:
backbone: UNet-S5-D16 backbone: UNet-S5-D16
crop size: (128,128) crop size: (128,128)
lr schd: 40000 lr schd: 40000
memory (GB): 0.968 memory (GB): 0.968
Name: fcn_unet_s5-d16_128x128_40k_chase_db1
Results: Results:
- Task: Semantic Segmentation
Dataset: CHASE_DB1 Dataset: CHASE_DB1
Metrics: Metrics:
mIoU: 80.24 mIoU: 80.24
Task: Semantic Segmentation Config: configs/unet/fcn_unet_s5-d16_128x128_40k_chase_db1.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_chase_db1/fcn_unet_s5-d16_128x128_40k_chase_db1_20201223_191051-11543527.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_chase_db1/fcn_unet_s5-d16_128x128_40k_chase_db1_20201223_191051-11543527.pth
- Config: configs/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1.py - Name: pspnet_unet_s5-d16_128x128_40k_chase_db1
In Collection: unet In Collection: unet
Metadata: Metadata:
backbone: UNet-S5-D16 backbone: UNet-S5-D16
crop size: (128,128) crop size: (128,128)
lr schd: 40000 lr schd: 40000
memory (GB): 0.982 memory (GB): 0.982
Name: pspnet_unet_s5-d16_128x128_40k_chase_db1
Results: Results:
- Task: Semantic Segmentation
Dataset: CHASE_DB1 Dataset: CHASE_DB1
Metrics: Metrics:
mIoU: 80.36 mIoU: 80.36
Task: Semantic Segmentation Config: configs/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1/pspnet_unet_s5-d16_128x128_40k_chase_db1_20201227_181818-68d4e609.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1/pspnet_unet_s5-d16_128x128_40k_chase_db1_20201227_181818-68d4e609.pth
- Config: configs/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1.py - Name: deeplabv3_unet_s5-d16_128x128_40k_chase_db1
In Collection: unet In Collection: unet
Metadata: Metadata:
backbone: UNet-S5-D16 backbone: UNet-S5-D16
crop size: (128,128) crop size: (128,128)
lr schd: 40000 lr schd: 40000
memory (GB): 0.999 memory (GB): 0.999
Name: deeplabv3_unet_s5-d16_128x128_40k_chase_db1
Results: Results:
- Task: Semantic Segmentation
Dataset: CHASE_DB1 Dataset: CHASE_DB1
Metrics: Metrics:
mIoU: 80.47 mIoU: 80.47
Task: Semantic Segmentation Config: configs/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1/deeplabv3_unet_s5-d16_128x128_40k_chase_db1_20201226_094047-4c5aefa3.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1/deeplabv3_unet_s5-d16_128x128_40k_chase_db1_20201226_094047-4c5aefa3.pth
- Config: configs/unet/fcn_unet_s5-d16_256x256_40k_hrf.py - Name: fcn_unet_s5-d16_256x256_40k_hrf
In Collection: unet In Collection: unet
Metadata: Metadata:
backbone: UNet-S5-D16 backbone: UNet-S5-D16
crop size: (256,256) crop size: (256,256)
lr schd: 40000 lr schd: 40000
memory (GB): 2.525 memory (GB): 2.525
Name: fcn_unet_s5-d16_256x256_40k_hrf
Results: Results:
- Task: Semantic Segmentation
Dataset: HRF Dataset: HRF
Metrics: Metrics:
mIoU: 79.45 mIoU: 79.45
Task: Semantic Segmentation Config: configs/unet/fcn_unet_s5-d16_256x256_40k_hrf.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_256x256_40k_hrf/fcn_unet_s5-d16_256x256_40k_hrf_20201223_173724-d89cf1ed.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_256x256_40k_hrf/fcn_unet_s5-d16_256x256_40k_hrf_20201223_173724-d89cf1ed.pth
- Config: configs/unet/pspnet_unet_s5-d16_256x256_40k_hrf.py - Name: pspnet_unet_s5-d16_256x256_40k_hrf
In Collection: unet In Collection: unet
Metadata: Metadata:
backbone: UNet-S5-D16 backbone: UNet-S5-D16
crop size: (256,256) crop size: (256,256)
lr schd: 40000 lr schd: 40000
memory (GB): 2.588 memory (GB): 2.588
Name: pspnet_unet_s5-d16_256x256_40k_hrf
Results: Results:
- Task: Semantic Segmentation
Dataset: HRF Dataset: HRF
Metrics: Metrics:
mIoU: 80.07 mIoU: 80.07
Task: Semantic Segmentation Config: configs/unet/pspnet_unet_s5-d16_256x256_40k_hrf.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_256x256_40k_hrf/pspnet_unet_s5-d16_256x256_40k_hrf_20201227_181818-fdb7e29b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_256x256_40k_hrf/pspnet_unet_s5-d16_256x256_40k_hrf_20201227_181818-fdb7e29b.pth
- Config: configs/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf.py - Name: deeplabv3_unet_s5-d16_256x256_40k_hrf
In Collection: unet In Collection: unet
Metadata: Metadata:
backbone: UNet-S5-D16 backbone: UNet-S5-D16
crop size: (256,256) crop size: (256,256)
lr schd: 40000 lr schd: 40000
memory (GB): 2.604 memory (GB): 2.604
Name: deeplabv3_unet_s5-d16_256x256_40k_hrf
Results: Results:
- Task: Semantic Segmentation
Dataset: HRF Dataset: HRF
Metrics: Metrics:
mIoU: 80.21 mIoU: 80.21
Task: Semantic Segmentation Config: configs/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf/deeplabv3_unet_s5-d16_256x256_40k_hrf_20201226_094047-3a1fdf85.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf/deeplabv3_unet_s5-d16_256x256_40k_hrf_20201226_094047-3a1fdf85.pth

9
configs/upernet/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/CSAILVision/unifiedparsing">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/pdf/1807.10221.pdf">UPerNet (ECCV'2018)</a></summary>
```latex ```latex
@inproceedings{xiao2018unified, @inproceedings{xiao2018unified,
title={Unified perceptual parsing for scene understanding}, title={Unified perceptual parsing for scene understanding},
@ -14,6 +21,8 @@
} }
``` ```
</details>
## Results and models ## Results and models
### Cityscapes ### Cityscapes

173
configs/upernet/upernet.yml
View File

@ -1,296 +1,305 @@
Collections: Collections:
- Metadata: - Name: upernet
Metadata:
Training Data: Training Data:
- Cityscapes - Cityscapes
- ADE20K - ADE20K
- Pascal VOC 2012 + Aug - Pascal VOC 2012 + Aug
Name: upernet Paper:
URL: https://arxiv.org/pdf/1807.10221.pdf
Title: Unified Perceptual Parsing for Scene Understanding
README: configs/upernet/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/uper_head.py#L13
Version: v0.17.0
Converted From:
Code: https://github.com/CSAILVision/unifiedparsing
Models: Models:
- Config: configs/upernet/upernet_r50_512x1024_40k_cityscapes.py - Name: upernet_r50_512x1024_40k_cityscapes
In Collection: upernet In Collection: upernet
Metadata: Metadata:
backbone: R-50 backbone: R-50
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 235.29
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 235.29
lr schd: 40000
memory (GB): 6.4 memory (GB): 6.4
Name: upernet_r50_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.1 mIoU: 77.1
mIoU(ms+flip): 78.37 mIoU(ms+flip): 78.37
Task: Semantic Segmentation Config: configs/upernet/upernet_r50_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_40k_cityscapes/upernet_r50_512x1024_40k_cityscapes_20200605_094827-aa54cb54.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_40k_cityscapes/upernet_r50_512x1024_40k_cityscapes_20200605_094827-aa54cb54.pth
- Config: configs/upernet/upernet_r101_512x1024_40k_cityscapes.py - Name: upernet_r101_512x1024_40k_cityscapes
In Collection: upernet In Collection: upernet
Metadata: Metadata:
backbone: R-101 backbone: R-101
crop size: (512,1024) crop size: (512,1024)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 263.85
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,1024) resolution: (512,1024)
value: 263.85
lr schd: 40000
memory (GB): 7.4 memory (GB): 7.4
Name: upernet_r101_512x1024_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.69 mIoU: 78.69
mIoU(ms+flip): 80.11 mIoU(ms+flip): 80.11
Task: Semantic Segmentation Config: configs/upernet/upernet_r101_512x1024_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_40k_cityscapes/upernet_r101_512x1024_40k_cityscapes_20200605_094933-ebce3b10.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_40k_cityscapes/upernet_r101_512x1024_40k_cityscapes_20200605_094933-ebce3b10.pth
- Config: configs/upernet/upernet_r50_769x769_40k_cityscapes.py - Name: upernet_r50_769x769_40k_cityscapes
In Collection: upernet In Collection: upernet
Metadata: Metadata:
backbone: R-50 backbone: R-50
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 568.18
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 568.18
lr schd: 40000
memory (GB): 7.2 memory (GB): 7.2
Name: upernet_r50_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 77.98 mIoU: 77.98
mIoU(ms+flip): 79.7 mIoU(ms+flip): 79.7
Task: Semantic Segmentation Config: configs/upernet/upernet_r50_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_40k_cityscapes/upernet_r50_769x769_40k_cityscapes_20200530_033048-92d21539.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_40k_cityscapes/upernet_r50_769x769_40k_cityscapes_20200530_033048-92d21539.pth
- Config: configs/upernet/upernet_r101_769x769_40k_cityscapes.py - Name: upernet_r101_769x769_40k_cityscapes
In Collection: upernet In Collection: upernet
Metadata: Metadata:
backbone: R-101 backbone: R-101
crop size: (769,769) crop size: (769,769)
lr schd: 40000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 641.03
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (769,769) resolution: (769,769)
value: 641.03
lr schd: 40000
memory (GB): 8.4 memory (GB): 8.4
Name: upernet_r101_769x769_40k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.03 mIoU: 79.03
mIoU(ms+flip): 80.77 mIoU(ms+flip): 80.77
Task: Semantic Segmentation Config: configs/upernet/upernet_r101_769x769_40k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_40k_cityscapes/upernet_r101_769x769_40k_cityscapes_20200530_040819-83c95d01.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_40k_cityscapes/upernet_r101_769x769_40k_cityscapes_20200530_040819-83c95d01.pth
- Config: configs/upernet/upernet_r50_512x1024_80k_cityscapes.py - Name: upernet_r50_512x1024_80k_cityscapes
In Collection: upernet In Collection: upernet
Metadata: Metadata:
backbone: R-50 backbone: R-50
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: upernet_r50_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 78.19 mIoU: 78.19
mIoU(ms+flip): 79.19 mIoU(ms+flip): 79.19
Task: Semantic Segmentation Config: configs/upernet/upernet_r50_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_80k_cityscapes/upernet_r50_512x1024_80k_cityscapes_20200607_052207-848beca8.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_80k_cityscapes/upernet_r50_512x1024_80k_cityscapes_20200607_052207-848beca8.pth
- Config: configs/upernet/upernet_r101_512x1024_80k_cityscapes.py - Name: upernet_r101_512x1024_80k_cityscapes
In Collection: upernet In Collection: upernet
Metadata: Metadata:
backbone: R-101 backbone: R-101
crop size: (512,1024) crop size: (512,1024)
lr schd: 80000 lr schd: 80000
Name: upernet_r101_512x1024_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.4 mIoU: 79.4
mIoU(ms+flip): 80.46 mIoU(ms+flip): 80.46
Task: Semantic Segmentation Config: configs/upernet/upernet_r101_512x1024_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_80k_cityscapes/upernet_r101_512x1024_80k_cityscapes_20200607_002403-f05f2345.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_80k_cityscapes/upernet_r101_512x1024_80k_cityscapes_20200607_002403-f05f2345.pth
- Config: configs/upernet/upernet_r50_769x769_80k_cityscapes.py - Name: upernet_r50_769x769_80k_cityscapes
In Collection: upernet In Collection: upernet
Metadata: Metadata:
backbone: R-50 backbone: R-50
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: upernet_r50_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 79.39 mIoU: 79.39
mIoU(ms+flip): 80.92 mIoU(ms+flip): 80.92
Task: Semantic Segmentation Config: configs/upernet/upernet_r50_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_80k_cityscapes/upernet_r50_769x769_80k_cityscapes_20200607_005107-82ae7d15.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_80k_cityscapes/upernet_r50_769x769_80k_cityscapes_20200607_005107-82ae7d15.pth
- Config: configs/upernet/upernet_r101_769x769_80k_cityscapes.py - Name: upernet_r101_769x769_80k_cityscapes
In Collection: upernet In Collection: upernet
Metadata: Metadata:
backbone: R-101 backbone: R-101
crop size: (769,769) crop size: (769,769)
lr schd: 80000 lr schd: 80000
Name: upernet_r101_769x769_80k_cityscapes
Results: Results:
- Task: Semantic Segmentation
Dataset: Cityscapes Dataset: Cityscapes
Metrics: Metrics:
mIoU: 80.1 mIoU: 80.1
mIoU(ms+flip): 81.49 mIoU(ms+flip): 81.49
Task: Semantic Segmentation Config: configs/upernet/upernet_r101_769x769_80k_cityscapes.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_80k_cityscapes/upernet_r101_769x769_80k_cityscapes_20200607_001014-082fc334.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_80k_cityscapes/upernet_r101_769x769_80k_cityscapes_20200607_001014-082fc334.pth
- Config: configs/upernet/upernet_r50_512x512_80k_ade20k.py - Name: upernet_r50_512x512_80k_ade20k
In Collection: upernet In Collection: upernet
Metadata: Metadata:
backbone: R-50 backbone: R-50
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 42.74
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 42.74
lr schd: 80000
memory (GB): 8.1 memory (GB): 8.1
Name: upernet_r50_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 40.7 mIoU: 40.7
mIoU(ms+flip): 41.81 mIoU(ms+flip): 41.81
Task: Semantic Segmentation Config: configs/upernet/upernet_r50_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_80k_ade20k/upernet_r50_512x512_80k_ade20k_20200614_144127-ecc8377b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_80k_ade20k/upernet_r50_512x512_80k_ade20k_20200614_144127-ecc8377b.pth
- Config: configs/upernet/upernet_r101_512x512_80k_ade20k.py - Name: upernet_r101_512x512_80k_ade20k
In Collection: upernet In Collection: upernet
Metadata: Metadata:
backbone: R-101 backbone: R-101
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 49.16
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 49.16
lr schd: 80000
memory (GB): 9.1 memory (GB): 9.1
Name: upernet_r101_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.91 mIoU: 42.91
mIoU(ms+flip): 43.96 mIoU(ms+flip): 43.96
Task: Semantic Segmentation Config: configs/upernet/upernet_r101_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_80k_ade20k/upernet_r101_512x512_80k_ade20k_20200614_185117-32e4db94.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_80k_ade20k/upernet_r101_512x512_80k_ade20k_20200614_185117-32e4db94.pth
- Config: configs/upernet/upernet_r50_512x512_160k_ade20k.py - Name: upernet_r50_512x512_160k_ade20k
In Collection: upernet In Collection: upernet
Metadata: Metadata:
backbone: R-50 backbone: R-50
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: upernet_r50_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.05 mIoU: 42.05
mIoU(ms+flip): 42.78 mIoU(ms+flip): 42.78
Task: Semantic Segmentation Config: configs/upernet/upernet_r50_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_160k_ade20k/upernet_r50_512x512_160k_ade20k_20200615_184328-8534de8d.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_160k_ade20k/upernet_r50_512x512_160k_ade20k_20200615_184328-8534de8d.pth
- Config: configs/upernet/upernet_r101_512x512_160k_ade20k.py - Name: upernet_r101_512x512_160k_ade20k
In Collection: upernet In Collection: upernet
Metadata: Metadata:
backbone: R-101 backbone: R-101
crop size: (512,512) crop size: (512,512)
lr schd: 160000 lr schd: 160000
Name: upernet_r101_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 43.82 mIoU: 43.82
mIoU(ms+flip): 44.85 mIoU(ms+flip): 44.85
Task: Semantic Segmentation Config: configs/upernet/upernet_r101_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_160k_ade20k/upernet_r101_512x512_160k_ade20k_20200615_161951-91b32684.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_160k_ade20k/upernet_r101_512x512_160k_ade20k_20200615_161951-91b32684.pth
- Config: configs/upernet/upernet_r50_512x512_20k_voc12aug.py - Name: upernet_r50_512x512_20k_voc12aug
In Collection: upernet In Collection: upernet
Metadata: Metadata:
backbone: R-50 backbone: R-50
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 43.16
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 43.16
lr schd: 20000
memory (GB): 6.4 memory (GB): 6.4
Name: upernet_r50_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 74.82 mIoU: 74.82
mIoU(ms+flip): 76.35 mIoU(ms+flip): 76.35
Task: Semantic Segmentation Config: configs/upernet/upernet_r50_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_20k_voc12aug/upernet_r50_512x512_20k_voc12aug_20200617_165330-5b5890a7.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_20k_voc12aug/upernet_r50_512x512_20k_voc12aug_20200617_165330-5b5890a7.pth
- Config: configs/upernet/upernet_r101_512x512_20k_voc12aug.py - Name: upernet_r101_512x512_20k_voc12aug
In Collection: upernet In Collection: upernet
Metadata: Metadata:
backbone: R-101 backbone: R-101
crop size: (512,512) crop size: (512,512)
lr schd: 20000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 50.05
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 50.05
lr schd: 20000
memory (GB): 7.5 memory (GB): 7.5
Name: upernet_r101_512x512_20k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 77.1 mIoU: 77.1
mIoU(ms+flip): 78.29 mIoU(ms+flip): 78.29
Task: Semantic Segmentation Config: configs/upernet/upernet_r101_512x512_20k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_20k_voc12aug/upernet_r101_512x512_20k_voc12aug_20200617_165629-f14e7f27.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_20k_voc12aug/upernet_r101_512x512_20k_voc12aug_20200617_165629-f14e7f27.pth
- Config: configs/upernet/upernet_r50_512x512_40k_voc12aug.py - Name: upernet_r50_512x512_40k_voc12aug
In Collection: upernet In Collection: upernet
Metadata: Metadata:
backbone: R-50 backbone: R-50
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: upernet_r50_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 75.92 mIoU: 75.92
mIoU(ms+flip): 77.44 mIoU(ms+flip): 77.44
Task: Semantic Segmentation Config: configs/upernet/upernet_r50_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_40k_voc12aug/upernet_r50_512x512_40k_voc12aug_20200613_162257-ca9bcc6b.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_40k_voc12aug/upernet_r50_512x512_40k_voc12aug_20200613_162257-ca9bcc6b.pth
- Config: configs/upernet/upernet_r101_512x512_40k_voc12aug.py - Name: upernet_r101_512x512_40k_voc12aug
In Collection: upernet In Collection: upernet
Metadata: Metadata:
backbone: R-101 backbone: R-101
crop size: (512,512) crop size: (512,512)
lr schd: 40000 lr schd: 40000
Name: upernet_r101_512x512_40k_voc12aug
Results: Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug Dataset: Pascal VOC 2012 + Aug
Metrics: Metrics:
mIoU: 77.43 mIoU: 77.43
mIoU(ms+flip): 78.56 mIoU(ms+flip): 78.56
Task: Semantic Segmentation Config: configs/upernet/upernet_r101_512x512_40k_voc12aug.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_40k_voc12aug/upernet_r101_512x512_40k_voc12aug_20200613_163549-e26476ac.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_40k_voc12aug/upernet_r101_512x512_40k_voc12aug_20200613_163549-e26476ac.pth

9
configs/vit/README.md
View File

@ -4,6 +4,13 @@
<!-- [ALGORITHM] --> <!-- [ALGORITHM] -->
<a href="https://github.com/google-research/vision_transformer">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98">Code Snippet</a>
<details>
<summary align="right"><a href="https://arxiv.org/pdf/2010.11929.pdf">Vision Transformer (ICLR'2021)</a></summary>
```latex ```latex
@article{dosoViTskiy2020, @article{dosoViTskiy2020,
title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale}, title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
@ -13,6 +20,8 @@
} }
``` ```
</details>
## Usage ## Usage
To use other repositories' pre-trained models, it is necessary to convert keys. To use other repositories' pre-trained models, it is necessary to convert keys.

167
configs/vit/vit.yml
View File

@ -1,248 +1,257 @@
Collections: Collections:
- Metadata: - Name: vit
Metadata:
Training Data: Training Data:
- ADE20K - ADE20K
Name: vit Paper:
URL: https://arxiv.org/pdf/2010.11929.pdf
Title: Vision Transformer
README: configs/vit/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
Version: v0.17.0
Converted From:
Code: https://github.com/google-research/vision_transformer
Models: Models:
- Config: configs/vit/upernet_vit-b16_mln_512x512_80k_ade20k.py - Name: upernet_vit-b16_mln_512x512_80k_ade20k
In Collection: vit In Collection: vit
Metadata: Metadata:
backbone: ViT-B + MLN backbone: ViT-B + MLN
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 144.09
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 144.09
lr schd: 80000
memory (GB): 9.2 memory (GB): 9.2
Name: upernet_vit-b16_mln_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 47.71 mIoU: 47.71
mIoU(ms+flip): 49.51 mIoU(ms+flip): 49.51
Task: Semantic Segmentation Config: configs/vit/upernet_vit-b16_mln_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/upernet_vit-b16_mln_512x512_80k_ade20k_20210624_130547-0403cee1.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/upernet_vit-b16_mln_512x512_80k_ade20k_20210624_130547-0403cee1.pth
- Config: configs/vit/upernet_vit-b16_mln_512x512_160k_ade20k.py - Name: upernet_vit-b16_mln_512x512_160k_ade20k
In Collection: vit In Collection: vit
Metadata: Metadata:
backbone: ViT-B + MLN backbone: ViT-B + MLN
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 131.93
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 131.93
lr schd: 160000
memory (GB): 9.2 memory (GB): 9.2
Name: upernet_vit-b16_mln_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 46.75 mIoU: 46.75
mIoU(ms+flip): 48.46 mIoU(ms+flip): 48.46
Task: Semantic Segmentation Config: configs/vit/upernet_vit-b16_mln_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/upernet_vit-b16_mln_512x512_160k_ade20k_20210624_130547-852fa768.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/upernet_vit-b16_mln_512x512_160k_ade20k_20210624_130547-852fa768.pth
- Config: configs/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k.py - Name: upernet_vit-b16_ln_mln_512x512_160k_ade20k
In Collection: vit In Collection: vit
Metadata: Metadata:
backbone: ViT-B + LN + MLN backbone: ViT-B + LN + MLN
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 146.63
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 146.63
lr schd: 160000
memory (GB): 9.21 memory (GB): 9.21
Name: upernet_vit-b16_ln_mln_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 47.73 mIoU: 47.73
mIoU(ms+flip): 49.95 mIoU(ms+flip): 49.95
Task: Semantic Segmentation Config: configs/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/upernet_vit-b16_ln_mln_512x512_160k_ade20k_20210621_172828-f444c077.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/upernet_vit-b16_ln_mln_512x512_160k_ade20k_20210621_172828-f444c077.pth
- Config: configs/vit/upernet_deit-s16_512x512_80k_ade20k.py - Name: upernet_deit-s16_512x512_80k_ade20k
In Collection: vit In Collection: vit
Metadata: Metadata:
backbone: DeiT-S backbone: DeiT-S
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 33.5
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 33.5
lr schd: 80000
memory (GB): 4.68 memory (GB): 4.68
Name: upernet_deit-s16_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.96 mIoU: 42.96
mIoU(ms+flip): 43.79 mIoU(ms+flip): 43.79
Task: Semantic Segmentation Config: configs/vit/upernet_deit-s16_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/upernet_deit-s16_512x512_80k_ade20k_20210624_095228-afc93ec2.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/upernet_deit-s16_512x512_80k_ade20k_20210624_095228-afc93ec2.pth
- Config: configs/vit/upernet_deit-s16_512x512_160k_ade20k.py - Name: upernet_deit-s16_512x512_160k_ade20k
In Collection: vit In Collection: vit
Metadata: Metadata:
backbone: DeiT-S backbone: DeiT-S
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 34.26
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 34.26
lr schd: 160000
memory (GB): 4.68 memory (GB): 4.68
Name: upernet_deit-s16_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 42.87 mIoU: 42.87
mIoU(ms+flip): 43.79 mIoU(ms+flip): 43.79
Task: Semantic Segmentation Config: configs/vit/upernet_deit-s16_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/upernet_deit-s16_512x512_160k_ade20k_20210621_160903-5110d916.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/upernet_deit-s16_512x512_160k_ade20k_20210621_160903-5110d916.pth
- Config: configs/vit/upernet_deit-s16_mln_512x512_160k_ade20k.py - Name: upernet_deit-s16_mln_512x512_160k_ade20k
In Collection: vit In Collection: vit
Metadata: Metadata:
backbone: DeiT-S + MLN backbone: DeiT-S + MLN
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 89.45
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 89.45
lr schd: 160000
memory (GB): 5.69 memory (GB): 5.69
Name: upernet_deit-s16_mln_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 43.82 mIoU: 43.82
mIoU(ms+flip): 45.07 mIoU(ms+flip): 45.07
Task: Semantic Segmentation Config: configs/vit/upernet_deit-s16_mln_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/upernet_deit-s16_mln_512x512_160k_ade20k_20210621_161021-fb9a5dfb.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/upernet_deit-s16_mln_512x512_160k_ade20k_20210621_161021-fb9a5dfb.pth
- Config: configs/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k.py - Name: upernet_deit-s16_ln_mln_512x512_160k_ade20k
In Collection: vit In Collection: vit
Metadata: Metadata:
backbone: DeiT-S + LN + MLN backbone: DeiT-S + LN + MLN
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 80.71
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 80.71
lr schd: 160000
memory (GB): 5.69 memory (GB): 5.69
Name: upernet_deit-s16_ln_mln_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 43.52 mIoU: 43.52
mIoU(ms+flip): 45.01 mIoU(ms+flip): 45.01
Task: Semantic Segmentation Config: configs/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/upernet_deit-s16_ln_mln_512x512_160k_ade20k_20210621_161021-c0cd652f.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/upernet_deit-s16_ln_mln_512x512_160k_ade20k_20210621_161021-c0cd652f.pth
- Config: configs/vit/upernet_deit-b16_512x512_80k_ade20k.py - Name: upernet_deit-b16_512x512_80k_ade20k
In Collection: vit In Collection: vit
Metadata: Metadata:
backbone: DeiT-B backbone: DeiT-B
crop size: (512,512) crop size: (512,512)
lr schd: 80000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 103.2
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 103.2
lr schd: 80000
memory (GB): 7.75 memory (GB): 7.75
Name: upernet_deit-b16_512x512_80k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 45.24 mIoU: 45.24
mIoU(ms+flip): 46.73 mIoU(ms+flip): 46.73
Task: Semantic Segmentation Config: configs/vit/upernet_deit-b16_512x512_80k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/upernet_deit-b16_512x512_80k_ade20k_20210624_130529-1e090789.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/upernet_deit-b16_512x512_80k_ade20k_20210624_130529-1e090789.pth
- Config: configs/vit/upernet_deit-b16_512x512_160k_ade20k.py - Name: upernet_deit-b16_512x512_160k_ade20k
In Collection: vit In Collection: vit
Metadata: Metadata:
backbone: DeiT-B backbone: DeiT-B
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 96.25
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 96.25
lr schd: 160000
memory (GB): 7.75 memory (GB): 7.75
Name: upernet_deit-b16_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 45.36 mIoU: 45.36
mIoU(ms+flip): 47.16 mIoU(ms+flip): 47.16
Task: Semantic Segmentation Config: configs/vit/upernet_deit-b16_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/upernet_deit-b16_512x512_160k_ade20k_20210621_180100-828705d7.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/upernet_deit-b16_512x512_160k_ade20k_20210621_180100-828705d7.pth
- Config: configs/vit/upernet_deit-b16_mln_512x512_160k_ade20k.py - Name: upernet_deit-b16_mln_512x512_160k_ade20k
In Collection: vit In Collection: vit
Metadata: Metadata:
backbone: DeiT-B + MLN backbone: DeiT-B + MLN
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 128.53
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 128.53
lr schd: 160000
memory (GB): 9.21 memory (GB): 9.21
Name: upernet_deit-b16_mln_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 45.46 mIoU: 45.46
mIoU(ms+flip): 47.16 mIoU(ms+flip): 47.16
Task: Semantic Segmentation Config: configs/vit/upernet_deit-b16_mln_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/upernet_deit-b16_mln_512x512_160k_ade20k_20210621_191949-4e1450f3.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/upernet_deit-b16_mln_512x512_160k_ade20k_20210621_191949-4e1450f3.pth
- Config: configs/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k.py - Name: upernet_deit-b16_ln_mln_512x512_160k_ade20k
In Collection: vit In Collection: vit
Metadata: Metadata:
backbone: DeiT-B + LN + MLN backbone: DeiT-B + LN + MLN
crop size: (512,512) crop size: (512,512)
lr schd: 160000
inference time (ms/im): inference time (ms/im):
- backend: PyTorch - value: 129.03
batch size: 1
hardware: V100 hardware: V100
backend: PyTorch
batch size: 1
mode: FP32 mode: FP32
resolution: (512,512) resolution: (512,512)
value: 129.03
lr schd: 160000
memory (GB): 9.21 memory (GB): 9.21
Name: upernet_deit-b16_ln_mln_512x512_160k_ade20k
Results: Results:
- Task: Semantic Segmentation
Dataset: ADE20K Dataset: ADE20K
Metrics: Metrics:
mIoU: 45.37 mIoU: 45.37
mIoU(ms+flip): 47.23 mIoU(ms+flip): 47.23
Task: Semantic Segmentation Config: configs/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/upernet_deit-b16_ln_mln_512x512_160k_ade20k_20210623_153535-8a959c14.pth Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/upernet_deit-b16_ln_mln_512x512_160k_ade20k_20210623_153535-8a959c14.pth