charlie880624/STDC
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
448 Commits 1 Branch 0 Tags
Commit Graph

448 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
chingning.chen
0287f0a0fa doc: update README.md -> kneron README.md 2022-04-15 16:30:19 +08:00
EricWu
d17be441c6 Merge branch 'update_stdc_doc' into 'Kn_dev_v0.21.1' 
doc: update stdc step-by-step

See merge request eric_wu/mmsegmentation!7
 2022-04-15 14:41:54 +08:00
chingning.chen
c447bdc86d doc: update stdc_step_by_step: some typos and minor fixes 2022-04-15 14:35:06 +08:00
EricChunYi
b6108b81cb doc: update stdc step-by-step 2022-04-14 18:19:02 +08:00
kiddjacky
07ffff5145
Initial commit 2022-04-12 22:14:55 -07:00
EricWu
ec2289d5c4 Merge branch 'style/pep8' into 'Kn_dev_v0.21.1' 
style: fix format so pep8 is satisfied

See merge request eric_wu/mmsegmentation!6
 2022-04-12 14:44:23 +08:00
chingning.chen
0136a5b2bd style: fix format so pep8 is satisfied 2022-04-12 14:26:54 +08:00
EricWu
a783220efa Merge branch 'style/pytorch2onnx_kneron' into 'Kn_dev_v0.21.1' 
style: pytorch2onnx_kneron.py line too long

See merge request eric_wu/mmsegmentation!5
 2022-04-11 16:01:16 +08:00
chingning.chen
b324a669c7 style: pytorch2onnx_kneron.py line too long 2022-04-11 15:53:36 +08:00
Chingning Chen
ef31f37c94 Merge branch 'modify_lincense' into 'Kn_dev_v0.21.1' 
use shorter kneron license line

See merge request eric_wu/mmsegmentation!4
 2022-04-11 11:51:08 +08:00
EricChunYi
f02cdeae3d use shorter kneron license line 2022-04-11 11:48:31 +08:00
Chingning Chen
a326bc75be Merge branch 'add_license' into 'Kn_dev_v0.21.1' 
add kneron license for kneron modified code

See merge request eric_wu/mmsegmentation!3
 2022-04-11 11:22:06 +08:00
EricChunYi
577de6d968 add kneron license for kneron modified code 2022-04-11 11:15:29 +08:00
EricWu
9eaf166bd5 Merge branch 'feat/pytorch2onnx_kneron' into 'Kn_dev_v0.21.1' 
Feat/pytorch2onnx kneron

See merge request eric_wu/mmsegmentation!1
 2022-04-11 10:34:18 +08:00
Chingning Chen
69a512ba98 Merge branch 'update_docs' into 'feat/pytorch2onnx_kneron' 
doc: revise step-by-step

See merge request eric_wu/mmsegmentation!2
 2022-04-07 16:00:54 +08:00
EricChunYi
48e6d06e5e doc: revise step-by-step 2022-04-07 15:58:59 +08:00
chingning.chen
7a2479fc0d chore: setup.py 2022-03-31 18:21:00 +08:00
chingning.chen
b97a324ad2 doc: step-by-step refactor 2022-03-31 18:14:50 +08:00
chingning.chen
79d82744ac Merge branch 'feat/pytorch2onnx_kneron' of 192.168.200.1:eric_wu/mmsegmentation into feat/pytorch2onnx_kneron 2022-03-31 18:14:36 +08:00
chingning.chen
9fe3811b86 chore: requirements update 2022-03-31 18:14:26 +08:00
chingning.chen
8f8f145abb doc: stdc_step_by_step 2022-03-31 17:35:11 +08:00
chingning.chen
fbfe81c815 feat: init_segmentor_kn, inference_segmentor_kn, show_result 2022-03-30 12:23:58 +08:00
chingning.chen
0563dd8847 tmp 2022-03-30 10:28:54 +08:00
chingning.chen
7576467aa1 refactor: remove final resize node from onnx; resize on app side 2022-03-29 17:59:50 +08:00
chingning.chen
dcac233a60 fix: shape assignment for deploy_test_kneron and pytorch2onnx_kneron 2022-03-29 17:43:55 +08:00
chingning.chen
4d7356fda7 chore: print for clarified information in pytorch2onnx_kneron 2022-03-28 16:45:55 +08:00
chingning.chen
caaa31c231 chore: normalization-in-onnx as an argument in pytorch2onnx_kneron 2022-03-28 16:43:00 +08:00
chingning.chen
b6a868c3e2 feat: onnx auto bn for kneron quantization 2022-03-25 17:03:14 +08:00
chingning.chen
0ec0b33ed7 fix: pytorch 1.10 generates ONNX with ir_version==7, which should be 6 2022-03-25 16:03:14 +08:00
chingning.chen
5b99260c9b feat: integrate kneron optimizer script to pytorch2onnx_kneron.py 2022-03-24 15:12:06 +08:00
chingning.chen
b83243c5f4 feat: slide mode for kneron onnx 2022-03-23 17:58:23 +08:00
chingning.chen
b2246495f5 refactor: not using MMDataParallel for onnx inferencing 2022-03-23 17:02:03 +08:00
chingning.chen
12c840564e refactor: run_with_iobinding -> run 2022-03-23 15:56:01 +08:00
chingning.chen
f824495134 fix: onnx inference wrong indexing bug 2022-03-23 10:28:58 +08:00
chingning.chen
5846e789be feat: deploy_test_kneron.py using ONNXRuntimeSegmentorKN 2022-03-21 17:04:29 +08:00
chingning.chen
3f2c7b18be feat: ONNXRuntimeSegmentorKN 2022-03-21 17:00:04 +08:00
chingning.chen
57bb510d5e feat: add stdc kn configs 2022-03-17 15:47:51 +08:00
chingning.chen
6b27600a1a feat: pytorch2onnx_kneron.py 2022-03-17 15:42:01 +08:00
MengzhangLI
a39f5856ce
Bump v0.21.1 (#1273) 
* Bump v0.21.1

* add improvements in changelog

* add improvements in changelog

* fix cn readme

* change changelog
 2022-02-09 17:17:55 +08:00
Jerry Jiarui XU
82a80880d2
[Improve] Add exception for PointRend for support CPU-only usage (#1271) 
* [Improve] Add exception for PointRend for support CPU-only usage

* fixed linting
 2022-02-09 00:52:56 -05:00
Jerry Jiarui XU
66b778c064
[Improve] Use MMCV load_state_dict func in ViT/Swin (#1272) 
* [Improve] Use MMCV load_state_dict func in ViT/Swin

* use CheckpointLoader instead
 2022-02-09 00:52:42 -05:00
MengzhangLI
b4314f98c1
[Enhancement] Upgrade isort in pre-commit hook (#1270) 2022-02-08 19:06:33 +08:00
MengzhangLI
af88b868a6
fix log repeat (#1267) 2022-02-08 13:40:19 +08:00
Range King
f599d388cf
[Docs] Fix typo (#1263) 
1. Fix img path typo in `useful_tools.md`, `zh_cn/model_zoo.md`, and `zh_cn/train.md`
2. Add missing content in `zh_cn/useful_tools.md` to to match `en/useful_tools.md`
 2022-02-07 23:20:29 +08:00
MengzhangLI
29cfcd145c
Bump v0.21.0 (#1258) 
* change version to v0.21.0

* change version to v0.21.0

* change version to v0.21.0

* change version to v0.21.0
 2022-01-29 18:30:13 +08:00
MengzhangLI
ecda117ea5
[Enhance] New-style CPU training and inference. (#1251) 
* [Enhance] New-style CPU training and inference.

* assert mmcv version

* SyncBN to BN in training and testing

* SyncBN to BN in training and testing

* upload untracked files to this branch

* delete gpu_ids

* fix bugs

* assert args.gpu_id in train.py

* use cfg.gpu_ids = [args.gpu_id]

* use cfg.gpu_ids = [args.gpu_id]

* fix typo

* fix typo

* fix typos
 2022-01-28 23:03:01 +08:00
MengzhangLI
02d2790145
delete unnecessary lines of STDCHead (#1231) 2022-01-28 10:53:11 +08:00
MengzhangLI
622f28eea3
[Fix] Fix bug in non-distributed multi-gpu training/testing (#1247) 
* Fix bug in non-distributed training

* Fix bug in non-distributed testing

* delete uncomment lines

* add args.gpus
 2022-01-28 10:38:16 +08:00
MengzhangLI
8ea3d64c65
add multi-processes script (#1238) 2022-01-27 21:18:55 +08:00
rstrudel
cb1bf9f372
[Feature] Support Segmenter (#955) 
* segmenter: add model

* update

* readme: update

* config: update

* segmenter: update readme

* segmenter: update

* segmenter: update

* segmenter: update

* configs: set checkpoint path to pretrain folder

* segmenter: modify vit-s/lin, remove data config

* rreadme: update

* configs: transfer from _base_ to segmenter

* configs: add 8x1 suffix

* configs: remove redundant lines

* configs: cleanup

* first attempt

* swipe CI error

* Update mmseg/models/decode_heads/__init__.py

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* segmenter_linear: use fcn backbone

* segmenter_mask: update

* models: add segmenter vit

* decoders: yapf+remove unused imports

* apply precommit

* segmenter/linear_head: fix

* segmenter/linear_header: fix

* segmenter: fix mask transformer

* fix error

* segmenter/mask_head: use trunc_normal init

* refactor segmenter head

* Fetch upstream (#1)

* [Feature] Change options to cfg-option (#1129)

* [Feature] Change option to cfg-option

* add expire date and fix the docs

* modify docstring

* [Fix] Add <!-- [ABSTRACT] --> in metafile #1127

* [Fix] Fix correct num_classes of HRNet in LoveDA dataset #1136

* Bump to v0.20.1 (#1138)

* bump version 0.20.1

* bump version 0.20.1

* [Fix] revise --option to --options #1140

Co-authored-by: Rockey <41846794+RockeyCoss@users.noreply.github.com>
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>

* decode_head: switch from linear to fcn

* fix init list formatting

* configs: remove variants, keep only vit-s on ade

* align inference metric of vit-s-mask

* configs: add vit t/b/l

* Update mmseg/models/decode_heads/segmenter_mask_head.py

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>

* Update mmseg/models/decode_heads/segmenter_mask_head.py

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>

* Update mmseg/models/decode_heads/segmenter_mask_head.py

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>

* Update mmseg/models/decode_heads/segmenter_mask_head.py

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>

* Update mmseg/models/decode_heads/segmenter_mask_head.py

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>

* model_converters: use torch instead of einops

* setup: remove einops

* segmenter_mask: fix missing imports

* add necessary imported init funtion

* segmenter/seg-l: set resolution to 640

* segmenter/seg-l: fix test size

* fix vitjax2mmseg

* add README and unittest

* fix unittest

* add docstring

* refactor config and add pretrained link

* fix typo

* add paper name in readme

* change segmenter config names

* fix typo in readme

* fix typos in readme

* fix segmenter typo

* fix segmenter typo

* delete redundant comma in config files

* delete redundant comma in config files

* fix convert script

* update lateset master version

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
Co-authored-by: Rockey <41846794+RockeyCoss@users.noreply.github.com>
Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
 2022-01-26 13:50:51 +08:00