b692ab740c
[Benchmark] Add BiSeNetV1 COCO-Stuff 164k benchmark ( #1019 )
...
* bisenetv1 on cocostuff164k
* change config_names & delete redundant keys
* pretrain should before lr.
* remove redundancy in bisenetv1_r50-d32
2021-11-17 00:12:02 -08:00
6d88b07084
fixing dice metric in unet ( #1041 )
2021-11-16 20:14:17 +08:00
008856a84c
[Fix] Remove `fp16` folder in `configs`. ( #1031 )
...
* remove fp16 folder
* remove fp16 in docs
* fix some typos
* fix some typos
* fix fp16 in yml
2021-11-15 19:14:57 +08:00
d4ec8ef963
fix EfficientMultiheadAttention in SegFormer ( #1037 )
2021-11-15 04:33:28 +08:00
bc27f24109
[Fix] Fix the bug that vit cannot load pretrain properly when using i… ( #999 )
...
* [Fix] Fix the bug that vit cannot load pretrain properly when using init_cfg to specify the pretrain scheme
* [Fix] fix the coverage problem
* Update mmseg/models/backbones/vit.py
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
* [Fix] make the predicate more concise and clearer
* [Fix] Modified the judgement logic
* Update tests/test_models/test_backbones/test_vit.py
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
* add comments
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
2021-11-03 10:36:09 -07:00
f013682ea0
delete benchmark_new.py ( #1012 )
2021-11-03 23:27:48 +08:00
28627a1288
Bump v0.19.0 ( #1009 )
...
* change version to v0.19.0
* update changelog
2021-11-03 05:27:20 +08:00
0a06853bb6
[Feature] Support TIMMBackbone ( #998 )
...
* add TIMMBackbone and unittests
* add timm to tests requirements
* deprecate pt1.3.1
* reduce the unittests input of timm backbone
* fix ci
* fix ci
* fix ci
* fix ci
* fix ci
* fix ci
* fix ci
* fix ci
* fix ci
* remove unittests of large models of timm backbone
* generate coverage report for all unittests env
* reduce the unittests input of timm backbone
* reduce the unittests input of timm backbone
2021-11-02 12:51:11 +08:00
4ea92ebbe6
smaller input & channels of unittest ( #1004 )
2021-11-01 07:47:43 -07:00
992d577783
[Fix] Change `self.loss_decode` back to `dict` in Single Loss situation. ( #1002 )
...
* fix single loss type
* fix error in ohem & point_head
* fix coverage miss
* fix uncoverage error of PointHead loss
* fix coverage miss
* fix uncoverage error of PointHead loss
* nn.modules.container.ModuleList to nn.ModuleList
* more simple format
* merge unittest def
2021-11-01 15:28:37 +08:00
d7f82e5dc8
Update train.py ( #428 )
...
* Update train.py
Add user-defined hooks.
* Update train.py
* Update train.py
2021-10-29 12:13:40 -07:00
4b69af7b13
Fix typo in usage example ( #1003 )
2021-10-29 01:06:49 +08:00
a33cbbf039
vit contiguous ( #992 )
2021-10-25 18:11:48 +08:00
b3d5cc3f17
[Docs] Fix the broken link ( #985 )
...
* [Fix] Fix the broken link
* [Fix] Fix the broken link
* Update docs/dataset_prepare.md
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
* Update docs_zh-CN/dataset_prepare.md
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
* [Docs] Fix the broken link
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
2021-10-25 15:07:40 +08:00
32f153e272
[Fix] Fix bug in CI with py3.9 ( #994 )
...
* remove python-dev in CI
* remove pycocotools installation
* remove python 3.9-dev installation dependencies
2021-10-24 11:49:07 -07:00
d8e7cfae21
[Benchmark] Uploading FastFCN on ADE20K ( #972 )
...
* Uploading FastFCN on ADE20K
* fixing lint error
2021-10-19 20:27:33 -07:00
67f1420472
[Enhancement] Add codespell pre-commit hook and fix typos ( #920 )
...
* add codespell pre-commit hook and fix typos
* Update mmseg/models/decode_heads/dpt_head.py
* Update mmseg/models/backbones/vit.py
* Update mmseg/models/backbones/vit.py
* fix typos
* skip formating typo
* deprecate formating
* skip ipynb
* unstage ipynb changes
* unstage ipynb changes
* fix typos in ipynb
* unstage ipynb changes
2021-10-13 06:21:17 -07:00
279b7e5d25
Change BiSeNetV2 to Method ( #945 )
2021-10-12 20:35:58 -07:00
d81554a642
first commit ( #946 )
2021-10-12 20:32:41 -07:00
7aa2680d16
fix the wrong description in the Chinese documentation ( #954 )
2021-10-12 20:39:02 +08:00
3c6cbc4a24
[Update] Update torchserve about ( #951 )
...
* test_torchserver1.1
* test_torchserver1.2
* update
* update mmseg_handler.py
* update docs
* update torchserver
* tranfer torchserver to torchserve
* update docs
* updata torchserve support
2021-10-12 19:56:02 +08:00
adb1cd361b
[Fix] Fix bug when loading class name form file in custom dataset ( #923 )
...
* [Fix] #916 expection string type classes
* add unittests for string path classes
* fix double quote string in test_dataset.py
* move the import to the top of the file
* fix isort lint error
fix isort lint error when move the import to the top of the file
2021-10-08 01:06:18 +08:00
1ce4904fe3
Bump to v0.18.0 ( #940 )
...
* bump to v0.18.0
* replace \ with /
2021-10-07 17:37:31 +08:00
fcc1c3b166
replace the unavailable pspnet model download address with the update… ( #934 )
...
* replace the unavailable pspnet model download address with the updated address
* replace the unavailable pspnet model download address with the updated address
2021-10-03 23:55:25 +08:00
a9d1295bc3
[Feature] Support FastFCN ( #885 )
...
* FastFCN first commit
* FastFCN first commit
* Fixing lint error
* Fixing lint error
* use for loop on JPU
* Use For Loop
* Refactor FastFCN
* FastFCN
* FastFCN
* temp
* Uploading models & logs (4x4)
* Fixing typos
* fix typos
* rename config
* change README.md
* use _delete_=True
* change configs
* change start_level to 0
* change start_level to 0
* jpu
* add unittest for start_level!=0
2021-10-01 02:41:24 +08:00
7db1cbb181
[Feature] Support ICNet ( #884 )
...
* add icnet backbone
* add icnet head
* add icnet configs
* nclass -> num_classes
* Support ICNet
* ICNet
* ICNet
* Add ICNeck
* Add ICNeck
* Add ICNeck
* Add ICNeck
* Adding unittest
* Uploading models & logs
* Uploading models & logs
* add comment
* smaller test_swin.py
* try to delete test_swin.py
* delete test_unet.py
* delete test_unet.py
* temp
* smaller test_unet.py
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
2021-09-30 09:31:57 -07:00
84edf6c190
fix load ckpt bug in swin ( #928 )
2021-09-30 07:50:44 -07:00
0cf56d48a4
change name to EncNet ( #929 )
2021-09-30 22:19:23 +08:00
7edc71d532
[Improvement] Refactor Swin-Transformer ( #800 )
...
* [Improvement] Refactor Swin-Transformer
* fixed swin test
* update patch emebd, add more tests
* fixed test
* remove pretrain_style
* fixed padding
* resolve coments
* use mmcv 2tuple
* refactor init_cfg
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
2021-09-29 08:46:33 +08:00
e701497a36
[Feature] Support BiSeNetV1 ( #851 )
...
* First Commit
* fix typos
* fix typos
* Fix assertion bug
* Adding Assert
* Adding Unittest
* Fixing typo
* Uploading models & logs
* Fixing unittest error
* changing README.md
* changing README.md
2021-09-29 02:12:57 +08:00
2800d43507
[Enhancement] Change readme style and Update metafiles. ( #895 )
...
* [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>
2021-09-28 16:25:37 +08:00
d96937a003
[Enhancement] Using docker to skip CUDA installation in CI ( #882 )
...
* Use docker to skip CUDA installation in CI
* Update .github/workflows/build.yml
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
* Remove Install system dependencies
* Add Install system dependencies for cuda usage
* Add Install system dependencies and requirements
* fix requirements error
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
2021-09-26 22:25:21 -07:00
f82e4d6fc9
[Feature] Support BiSeNetV2 ( #804 )
...
* BiSeNetV2 first commit
* BiSeNetV2 unittest
* remove pytest
* add pytest module
* fix ConvModule input name
* fix pytest error
* fix unittest
* refactor
* BiSeNetV2 Refactory
* fix docstrings and add some small changes
* use_sigmoid=False
* fix potential bugs about upsampling
* Use ConvModule instead
* Use ConvModule instead
* fix typos
* fix typos
* fix typos
* discard nn.conv2d
* discard nn.conv2d
* discard nn.conv2d
* delete **kwargs
* uploading markdown and model
* final commit
* BiSeNetV2 adding Unittest for its modules
* BiSeNetV2 adding Unittest for its modules
* BiSeNetV2 adding Unittest for its modules
* BiSeNetV2 adding Unittest for its modules
* BiSeNetV2 adding Unittest for its modules
* BiSeNetV2 adding Unittest for its modules
* BiSeNetV2 adding Unittest for its modules
* Fix README conflict
* Fix unittest problem
* Fix unittest problem
* BiSeNetV2
* Fixing fps
* Fixing typpos
* bisenetv2
2021-09-26 18:52:16 +08:00
96b369bd55
[Fix] Fix loss parse in val_step ( #906 )
...
* [Fix] Fix loss parse in val_step
* Add val_step unittest
* Add train_step unittest
2021-09-25 18:17:40 -07:00
575ee03957
The path of the annotation is wrong in the tutorial ( #907 )
...
* Update config.md
* Update config.md
2021-09-26 00:07:41 +08:00
0fd3972c41
[Feature] Support multiple losses during training ( #818 )
...
* multiple losses
* fix lint error
* fix typos
* fix typos
* Adding Attribute
* Fixing loss_ prefix
* Fixing loss_ prefix
* Fixing loss_ prefix
* Add Same
* loss_name must has 'loss_' prefix
* Fix unittest
* Fix unittest
* Fix unittest
* Update mmseg/models/decode_heads/decode_head.py
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
2021-09-24 15:08:28 +08:00
e13076adef
[Fix] fix_torchserver1.1 ( #844 )
...
* test_torchserver1.1
* test_torchserver1.2
* update
* update mmseg_handler.py
* update docs
* update torchserver
* tranfer torchserver to torchserve
* update docs
2021-09-23 19:14:52 +08:00
749abaa78c
Fixing README ( #896 )
2021-09-22 17:19:19 -07:00
bf1bdba623
support coco stuff-10k/164k ( #625 )
...
* support coco stuff-10k/164k
* update docs
* fix docs
* update docs
* fix import lints
* Update docs/dataset_prepare.md
* Update docs/dataset_prepare.md
* Update tools/convert_datasets/coco_stuff164k.py
* Update tools/convert_datasets/coco_stuff10k.py
* Update tools/convert_datasets/coco_stuff10k.py
* Update tools/convert_datasets/coco_stuff10k.py
* Update tools/convert_datasets/coco_stuff10k.py
* Update coco_stuff.py
fix the description of the dataset
* Update dataset_prepare.md
fix the doc tree of coco stuff 10k
* Update coco_stuff10k.py
fix img_dir
* Update coco_stuff.py
fix descriptions
* Update coco_stuff164k.py
fix out_dir
* Update coco_stuff10k.py
fix save file name
* Update coco_stuff.py
fix seg_map_suffix
* Update dataset_prepare.md
fix -p
* Update dataset_prepare.md
fix doc tree
* modify coco stuff convertor
* Remove redundant code
* fix 164k convert bug
* remove redundant comment
* add deeplabv3 configs and more iterations
* replace shutil.move with shtil.copyfile
* Update deeplabv3_r50-d8_512x512_4x4_80k_coco_stuff10k.py
fix wrong config
* Update deeplabv3_r101-d8_512x512_4x4_80k_coco_stuff164k.py
fix wrong config
* fix wrong configs
* fix wrong configs
* fix wrong path for coco stuff 10k
* fix convert bugs
* fix seg_filename bug
* when nproc=0, use track progress
* rename configs: coco_stuff --> coco-stuff
* add coco-stuff 10k and 164k to README.md
* update configs
* add deeplabv3 benchmark
* add pspnet benchmark
* remove redundant comma
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
2021-09-22 20:48:08 +08:00
6926712820
[Docs] Use Chinese menu ( #880 )
...
* Use Chinese menu
* replace \ with /
2021-09-18 18:36:43 +08:00
9162d058d9
[Docs] Improve docs style ( #879 )
...
* Improve docs style
* update lists
* update the size of image
* modify duplicate mmdet3d
2021-09-16 08:23:50 -07:00
9ac053f49a
[Fix] Convert SyncBN to BN when training on DP ( #772 )
...
* [Fix] Convert SyncBN to BN when training on DP.
* Modify SyncBN2BN.
* Add SyncBN2BN unit test.
* Resolve some comments.
* use mmcv official revert_sync_batchnorm
* Remove local syncbn2bn unit tests.
* Update mmcv version.
* Fix bugs of gather model tools.
* Modify warnings.
* Modify docker mmcv version.
* Update mmcv version table.
2021-09-15 09:39:37 -07:00
4583dc1033
[Enhancement] Support loading GT for evaluation from multi-file backend ( #867 )
...
* support load gt for evaluation from multi-backend
* move some code from get_gt_seg_maps to get_one_gt_seg_map
* rename gt_seg_map_loader_conf to gt_seg_map_loader_cfg
* fix doc str
* rename get_one_gt_seg_map to get_gt_seg_map_by_idx
2021-09-14 19:16:01 -07:00
730f36cd8b
[Fix] Update mmcv installation in dockerfile ( #860 )
...
* update dockerfile
* Update docker/Dockerfile
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
* add ARG
* change dash to bash
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
2021-09-11 14:34:35 +08:00
f3a49b56a4
[Fix] Fix iter bug when resuming checkpoint in distributed train ( #866 )
...
* [Fix] Fix iter bug when resuming checkpoint in distributed train
* fix lint error
Signed-off-by: FreyWang <wangwxyz@qq.com>
2021-09-11 14:33:01 +08:00
598f5c7fa8
[Feature] Support eval concate dataset and add tool to show dataset ( #833 )
...
* [Feature] Add tool to show origin or augmented train data
* [Feature] Support eval concate dataset
* Add docstring and modify evaluate of concate dataset
Signed-off-by: FreyWang <wangwxyz@qq.com>
* format concat dataset in subfolder of imgfile_prefix
Signed-off-by: FreyWang <wangwxyz@qq.com>
* add unittest of concate dataset
Signed-off-by: FreyWang <wangwxyz@qq.com>
* update unittest for eval dataset with CLASSES is None
Signed-off-by: FreyWang <wangwxyz@qq.com>
* [FIX] bug of generator, which lead metric to nan when pre_eval=False
Signed-off-by: FreyWang <wangwxyz@qq.com>
* format code
Signed-off-by: FreyWang <wangwxyz@qq.com>
* add more unittest
* add more unittest
* optim concat dataset builder
2021-09-09 13:00:23 +08:00
b0787b8be2
[Feature] Support ISA module ( #70 )
...
* add isa module
* use more readable names, add more comments and exp results
* add unittests
* remove redundant docstring
* Apply suggestions from code review
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
* fix unittest
* Update configs
* add results
* update yml
* Update README
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
Co-authored-by: xiexinch <xinchen.xie@qq.com>
2021-09-08 21:13:53 -07:00
6762958ea0
[Enhancement] Upgrade CI for PyTorch1.9 ( #712 )
...
* Upgrade CI for PyTorch1.9
* fix typo
* merge build_cu101 and build_cu102 to build_cuda
* fix substitution bug
* test
* test
* test
* test
* test
* test
* test
* test
* test
* test
* test
* test
* remove redudant items
* add python 3.9 to CI
* add python 3.9 to setup.py
* remove some versions of pytorch for python 3.9 test
* fix torch version error
* delete mim files
* update ubuntu version
* fix mmcv cuda version
2021-09-08 18:43:17 -07:00
d3dc4f9583
[Enhancement] Add Dev tools to boost develop ( #798 )
...
* Modify default work dir when training.
* Refactor gather_models.py.
* Add train and test matching list.
* Regression benchmark list.
* lower readme name to upper readme name.
* Add url check tool and model inference test tool.
* Modify tool name.
* Support duplicate mode of log json url check.
* Add regression benchmark evaluation automatic tool.
* Add train script generator.
* Only Support script running.
* Add evaluation results gather.
* Add exec Authority.
* Automatically make checkpoint root folder.
* Modify gather results save path.
* Coarse-grained train results gather tool.
* Complete benchmark train script.
* Make some little modifications.
* Fix checkpoint urls.
* Fix unet checkpoint urls.
* Fix fast scnn & fcn checkpoint url.
* Fix fast scnn checkpoint urls.
* Fix fast scnn url.
* Add differential results calculation.
* Add differential results of regression benchmark train results.
* Add an extra argument to select model.
* Update nonlocal_net & hrnet checkpoint url.
* Fix checkpoint url of hrnet and Fix some tta evaluation results and modify gather models tool.
* Modify fast scnn checkpoint url.
* Resolve new comments.
* Fix url check status code bug.
* Resolve some comments.
* Modify train scripts generator.
* Modify work_dir of regression benchmark results.
* model gather tool modification.
2021-09-02 09:44:51 -07:00
767de8f4d9
[Fix] Fix docstring link problem in readthedocs ( #845 )
...
* fix docstring link
* fix docstring link
* fix docstring link
* fix docstring link
* fix docstring link
* fix docstring link
2021-09-02 17:06:43 +08:00
MengzhangLI
Junjun2016
Rockey
gszh
lkm2835
Yuan Haobo
VVsssssk
Shouping Shan
VoyagerXVoyagerXisavailable
Jerry Jiarui XU
sennnnn
Julius Zhang
kira
DerrickWang005
uni19
FreyWang
Layne