117 lines
3.3 KiB
YAML
117 lines
3.3 KiB
YAML
Collections:
|
|
- Name: SCNet
|
|
Metadata:
|
|
Training Data: COCO
|
|
Training Techniques:
|
|
- SGD with Momentum
|
|
- Weight Decay
|
|
Training Resources: 8x V100 GPUs
|
|
Architecture:
|
|
- FPN
|
|
- ResNet
|
|
- SCNet
|
|
Paper:
|
|
URL: https://arxiv.org/abs/2012.10150
|
|
Title: 'SCNet: Training Inference Sample Consistency for Instance Segmentation'
|
|
README: configs/scnet/README.md
|
|
Code:
|
|
URL: https://github.com/open-mmlab/mmdetection/blob/v2.9.0/mmdet/models/detectors/scnet.py#L6
|
|
Version: v2.9.0
|
|
|
|
Models:
|
|
- Name: scnet_r50_fpn_1x_coco
|
|
In Collection: SCNet
|
|
Config: configs/scnet/scnet_r50_fpn_1x_coco.py
|
|
Metadata:
|
|
Training Memory (GB): 7.0
|
|
inference time (ms/im):
|
|
- value: 161.29
|
|
hardware: V100
|
|
backend: PyTorch
|
|
batch size: 1
|
|
mode: FP32
|
|
resolution: (800, 1333)
|
|
Epochs: 12
|
|
Results:
|
|
- Task: Object Detection
|
|
Dataset: COCO
|
|
Metrics:
|
|
box AP: 43.5
|
|
- Task: Instance Segmentation
|
|
Dataset: COCO
|
|
Metrics:
|
|
mask AP: 39.2
|
|
Weights: https://download.openmmlab.com/mmdetection/v2.0/scnet/scnet_r50_fpn_1x_coco/scnet_r50_fpn_1x_coco-c3f09857.pth
|
|
|
|
- Name: scnet_r50_fpn_20e_coco
|
|
In Collection: SCNet
|
|
Config: configs/scnet/scnet_r50_fpn_20e_coco.py
|
|
Metadata:
|
|
Training Memory (GB): 7.0
|
|
inference time (ms/im):
|
|
- value: 161.29
|
|
hardware: V100
|
|
backend: PyTorch
|
|
batch size: 1
|
|
mode: FP32
|
|
resolution: (800, 1333)
|
|
Epochs: 20
|
|
Results:
|
|
- Task: Object Detection
|
|
Dataset: COCO
|
|
Metrics:
|
|
box AP: 44.5
|
|
- Task: Instance Segmentation
|
|
Dataset: COCO
|
|
Metrics:
|
|
mask AP: 40.0
|
|
Weights: https://download.openmmlab.com/mmdetection/v2.0/scnet/scnet_r50_fpn_20e_coco/scnet_r50_fpn_20e_coco-a569f645.pth
|
|
|
|
- Name: scnet_r101_fpn_20e_coco
|
|
In Collection: SCNet
|
|
Config: configs/scnet/scnet_r101_fpn_20e_coco.py
|
|
Metadata:
|
|
Training Memory (GB): 8.9
|
|
inference time (ms/im):
|
|
- value: 172.41
|
|
hardware: V100
|
|
backend: PyTorch
|
|
batch size: 1
|
|
mode: FP32
|
|
resolution: (800, 1333)
|
|
Epochs: 20
|
|
Results:
|
|
- Task: Object Detection
|
|
Dataset: COCO
|
|
Metrics:
|
|
box AP: 45.8
|
|
- Task: Instance Segmentation
|
|
Dataset: COCO
|
|
Metrics:
|
|
mask AP: 40.9
|
|
Weights: https://download.openmmlab.com/mmdetection/v2.0/scnet/scnet_r101_fpn_20e_coco/scnet_r101_fpn_20e_coco-294e312c.pth
|
|
|
|
- Name: scnet_x101_64x4d_fpn_20e_coco
|
|
In Collection: SCNet
|
|
Config: configs/scnet/scnet_x101_64x4d_fpn_20e_coco.py
|
|
Metadata:
|
|
Training Memory (GB): 13.2
|
|
inference time (ms/im):
|
|
- value: 204.08
|
|
hardware: V100
|
|
backend: PyTorch
|
|
batch size: 1
|
|
mode: FP32
|
|
resolution: (800, 1333)
|
|
Epochs: 20
|
|
Results:
|
|
- Task: Object Detection
|
|
Dataset: COCO
|
|
Metrics:
|
|
box AP: 47.5
|
|
- Task: Instance Segmentation
|
|
Dataset: COCO
|
|
Metrics:
|
|
mask AP: 42.3
|
|
Weights: https://download.openmmlab.com/mmdetection/v2.0/scnet/scnet_x101_64x4d_fpn_20e_coco/scnet_x101_64x4d_fpn_20e_coco-fb09dec9.pth
|