Commit Graph

551 Commits (df6edd7f5a53cd6fa3a5c979fddf542fa926c671)
 

Author SHA1 Message Date
Ma Zerun a7f8e96b31
Bump version to v0.20.1 (#685) 2022-02-07 11:46:50 +08:00
mzr1996 e0edffb353 Merge branch 'dev' 2022-01-31 12:00:17 +08:00
Ma Zerun fb6d6f18d9
Bump version to v0.20.0 (#679)
* Bump version to v0.20.0

* Improve according to comments
2022-01-31 11:51:49 +08:00
Ma Zerun 8ef5aeda40
[Enhance] New-style CPU training and inference. (#674)
* [Enhance] New-style CPU training and inference.

* Add version check in CPU training/test
2022-01-30 20:49:54 +08:00
Ma Zerun 5de480ea9e
[Feature] Support HRNet and add pre-trained models (#660)
* Support HRNet

* Add HRNet configs

* Fix a bug in backward

* Add configs and update docs.

* Not use bias in conv before batch norm

* Defaults to use `norm_eval=False`

* Add unit tests and support out_channels in HRFuseScales

* Update checkpoint path

* Update docstring.

* Remove incorrect files

* Improve according to comments
2022-01-28 10:54:14 +08:00
Ma Zerun dc456a0c2c
[Feature] Support ConvNeXt (#670)
* Support ConvNeXt

* Add configs of ConvNeXt

* Update dev scripts

* Update docs.

* Use new style README

* Add unit tests.

* Update README

* Imporve according to comments

* Modify refers to timm.

* Imporve according to comments
2022-01-28 10:36:45 +08:00
xiatao 8488a784f0
[Fix] Fix potential unexcepted behaviors if `metric_options` is not specified in multi-label evaluation. (#647)
* Update multi_label.py

* Fix lint

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-01-27 10:27:38 +08:00
Ezra-Yu 94eb3ff83e
[Feature] Add Twins backbone and convert checkpoints. (#642)
* add twins backbone

* add position_encoding

* refactor twins

* Supplemental unit tests

* update docstring and readme

* update docstring and readme

* update docstring and readme

* update docstring

* update docstring

* update docstring

* update docstring

* remove note

* update doc and docstring

* update docstring

* update docstring

* use abstract pdf link and rename yamlfile

* Update model link

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-01-27 10:25:05 +08:00
Ma Zerun f552419e45
[Enhance] Add setup multi-processing both in train and test. (#671) 2022-01-27 10:18:36 +08:00
Ma Zerun 833152b1f4
[Docs] Update README in configs according to OpenMMLab standard. (#672)
* Update README according to OpenMMLab standard.

* Update model zoo docs generation.

* Revert modification for paperlink
2022-01-26 18:26:01 +08:00
mzr1996 a451d63d0e Avoid CI for PRs that only modifiy configs 2022-01-25 17:52:37 +08:00
Ezra-Yu bd397f790f
[Enhance] Rewrite channel split operation in ShufflenetV2 (#632)
* replace chunk op

* shufflenetv2 config
2022-01-25 14:45:28 +08:00
WINDSKY45 b5bd87d7fa
[Docs] Fix some typo in docs. 2022-01-25 12:32:06 +08:00
Ma Zerun a865d64208
[Refactor] Deprecate the support for "python setup.py test" (#646)
* Deprecate the support for "python setup.py test"

* Update requirements
2022-01-25 12:15:12 +08:00
Zhicheng Chen d56170a734
[Feature] Support EfficientNet (#649)
* add config for resnest test

* fix config

* add label smoothing

* add memcached

* minor fix

* fix bug

* fix config

* add config

* minor fix

* fix configs

* use EResize

* change interpolation

* add more configs

* add docsting

* add unittest

* remove unnecessary changes

* minor fix

* add more docstring

* fix linting

* add efficient backbone

* add config

* add Edge Residual

* fix bug

* remove unnecessary files

* refactor

* add resize in crop to ensure crop size is output size

* fix bug and add comments

* test

* fix

* add more configs

* add more configs

* add more configs

* fix bug

* add model zoo

* fix

* reorganize code

* add edge tpu

* add edge tpu converter

* rename

* update readme

* reorganize code and config

* Rename configs of EfficientNet, and add metafile & model_zoo

* Remove `backend='pillow'`

* Add comments about EfficientNet-EdgeTPU

* Rename the convert tool of EfficientNet.

* Refactor EfficientNet and update docstring.

* Update EfficientNet-EdgeTPU config

* Fix unit tests

Co-authored-by: lixinran <lixr423@outlook.com>
Co-authored-by: lixinran <lixinran@sensetime.com>
Co-authored-by: mzr1996 <mzr1996@163.com>
2022-01-25 12:14:17 +08:00
Yosuke Shinya 16864c7495
[Feature] Support features_only in TIMMBackbone (#668)
* Support features_only in TIMMBackbone

based on https://github.com/open-mmlab/mmsegmentation/pull/998

* update test for mmdet

* fix unit test for build_without_timm

* Update docstring

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-01-25 11:22:23 +08:00
xiefeifeihu 25f5cc7ea5
[Docs] Fix typo of `analysis.md`. (#664)
test.py not train.py
2022-01-22 10:39:23 +08:00
xiefeifeihu 9e6bf24ec1
[Docs] Fix typo in `analysis.md`. (#663)
示例脚本应执行“eval_metric.py”,而不是analyze_results.py。
另外应该是利用 `tools/test.py` 的 `--out` 参数,而不是`tools/train.py`
2022-01-22 10:38:43 +08:00
Ma Zerun 611a3fb309
[Docs] Update README.md (#655)
* Update README.md

* Update README_zh-CN.md

* Update README
2022-01-22 10:36:39 +08:00
Yusuke Minami e694269c59
[Enhance] Support single-label, softmax, custom eps by asymmetric loss (#609)
Co-authored-by: Minyus <Minyus@users.noreply.github.com>
2022-01-21 11:35:14 +08:00
takuoko d29037e8d1
[Enhance] Suport Mixup&Cutmix for multi-label task. 2022-01-21 11:30:58 +08:00
xiefeifeihu 1a91a7fed5
[Fix] Fix API changes in `pytorch-grad-cam>=1.3.7` (#656)
* Update vis_cam.py

Fix bug 654 temporary

* support grad-cam==1.3.7

Co-authored-by: Ezra-Yu <1105212286@qq.com>
2022-01-19 19:00:31 +08:00
xiefeifeihu d73eb01cba
[Fix] Fix bug which breaks `cal_train_time` in `analyze_logs.py`. (#662)
* fix bug mmclassification issues 661

https://github.com/open-mmlab/mmclassification/issues/661

* fix lint

Co-authored-by: Zhicheng Chen <chen1319276472@foxmail.com>
2022-01-19 18:38:48 +08:00
Ma Zerun b39885d953
[Feature] Support K-fold cross-validation (#563)
* Support to use `indices` to specify which samples to evaluate.

* Add KFoldDataset wrapper

* Rename 'K' to 'num_splits' accroding to sklearn

* Add `kfold-cross-valid.py`

* Add unit tests

* Add help doc and docstring
2022-01-19 18:32:55 +08:00
mzr1996 321ad09e6d Merge remote-tracking branch 'origin/master' into dev 2022-01-13 19:27:23 +08:00
Rejnald Lleshi c07f8326e3
[Feature] Add conversion script from pytroch to mlmodel (#597) 2022-01-13 12:32:52 +08:00
imyhxy 32d606e1a1
[Refactor] Save class names in best checkpoint created by evaluation hook (#641)
* Save class names in best checkpoint created by evaluation hook

* Save meta info into runner instaed of checkpoint_config
2022-01-13 12:20:59 +08:00
Ma Zerun 5232965b17
[Docs] Update install guide and README (#624)
* Update install guide

* Add new repos in README and use readthedocs link preferentially.

* Add MMRazor

* Improve README

* Imporve docs

* Imporve docs
2022-01-04 11:38:05 +08:00
Ma Zerun 7dfc9e4a85
Bump version to v0.19.0 (#623) 2021-12-31 12:55:47 +08:00
mzr1996 cdf569a805 Fix ResNet rsb config 2021-12-31 11:12:21 +08:00
mzr1996 e1a4020168 Fix ResNet rsb config 2021-12-31 11:08:11 +08:00
mzr1996 0a07d47b4a Update gitignore and docs requirements 2021-12-29 14:26:43 +08:00
Zhicheng Chen 0bbbb04429
[Enhancement] Improve the accuracy of ResNet (#572)
* add itp timm

* minor update

* minor update

* minor update

* add rep aug, minor update on configs

* minor update

* add target threshold

* add decaymulti

* minor update

* minor update

* add lbl smooth

* update lr

* reorganize config files and code

* minor bugfixes

* remove unused parts and minor fixes on cfg

* critical bugfix, add test and cfg update

* refactor code

* update doc string

* remove duplicate code

* refactor drop path in resnet

* rename

* Modify configs and add README&metafile

* Update metafile

Co-authored-by: mzr1996 <mzr1996@163.com>
2021-12-29 10:58:42 +08:00
Ezra-Yu e7c06b8541
[Reproduction] Reproduce RegNetX training accuracy. (#587)
* add preciseBN hook

* add precise-bn config

* add proority of preciseBN

* Add precise BN hook

* Update PreciseBN hook

* add config example & pre-commit

* Update PBN

* Add unit test

* Update unit tests

* mv preciseBN to mmcls.runner

* rm extra sleep()

* merge latest

* update code

* fix lint

* update unit tests

* add regnetx configs

* update prcise BN in configs

* fix lint

* add checkpoints and logs

* fix conflict

* fix lint

* update model_zoo and model-index

* remove some changes

* update readme.md

* remove precise_bn.py
2021-12-28 17:34:27 +08:00
Ma Zerun 159b38d276
[Reproduction] Reproduce training results of T2T-ViT (#610)
* Add cosine cool down lr updater

* Use ema hook

* Update decay mult

* Update configs.

* Update T2T-ViT readme and format all readme

* Update swin readme

* Update tnt readme

* Add docstring for `CosineAnnealingCooldownLrUpdaterHook`.

* Update t2t readme and metafile
2021-12-28 15:09:40 +08:00
Ezra-Yu d1d9ebfc67
[Feature] Add Precise BN (#401)
* add preciseBN hook

* add precise-bn config

* add proority of preciseBN

* Add precise BN hook

* Update PreciseBN hook

* add config example & pre-commit

* Update PBN

* Add unit test

* Update unit tests

* mv preciseBN to mmcls.runner

* rm extra sleep()

* merge latest

* update code

* fix lint

* update unit tests

* update unit tests and add warning

* update docstring and renamme filename

* remove model warpper

* add copyright

* Imporve docs and update some variable names

* Update resnet50_8xb32-coslr-preciseBN_in1k.py

Co-authored-by: mzr1996 <mzr1996@163.com>
2021-12-24 16:28:42 +08:00
Ezra-Yu 131d8c6296
[Feature] Add CAM visualization tool (#577)
* add cam-grad tool

* refactor cam-grad tool

* add docs

* update docs

* Update docs and support Transformer

* remove pictures and use link

* replace example img and finish EN docs

* improve docs

* improve code

* Fix MobileNet V3 configs

* Refactor to support more powerful feature extraction.

* Add unit tests

* Fix unit test

* fix distortion of visualization exapmles in docs

* fix distortion

* fix distortion

* fix distortion

* merge master

* merge fix conficts

* Imporve the tool

* Support use both attribute name and index to get layer

* add default get_target-layers

* add default get_target-layers

* update docs

* update docs

* add additional printt info when not using target-layers

* Imporve docs

* Fix enumerate list.

Co-authored-by: mzr1996 <mzr1996@163.com>
2021-12-23 18:53:40 +08:00
Zhicheng Chen da39ca6898
[Fix] Fix test sampler bug. (#611)
* sampler bugfixes

* sampler bugfixes

* reorganize code

* minor fixes

* reorganize code

* minor fixes

* Use `mmcv.runner.get_dist_info` instead of `dist` package to get rank
and world size.

* Add `build_dataloader` unit tests and fix sampler's unit tests.

* Fix unit tests

* Fix unit tests

Co-authored-by: mzr1996 <mzr1996@163.com>
2021-12-23 18:07:41 +08:00
Zhicheng Chen d5ae255061
[Feature] Repeated Aug and Sampler Registry (#588) 2021-12-21 15:26:28 +08:00
mzr1996 b4450b720e [Docs] Fix colab link 2021-12-17 18:07:19 +08:00
Ma Zerun 643fb192cd
[Enhance] Enhance feature extraction function. (#593)
* Fix MobileNet V3 configs

* Refactor to support more powerful feature extraction.

* Add unit tests

* Fix unit test

* Imporve according to comments

* Update checkpoints path

* Fix unit tests

* Add docstring of `simple_test`

* Add docstring of `extract_feat`

* Update model zoo
2021-12-17 15:55:02 +08:00
Ma Zerun f9a2b04cee
[Feature] Add DeiT backbone and checkpoints. (#576)
* Support DeiT backbone.

* Use hook to automatically resize pos embed

* Update ViT training setting

* Add deit configs and update docs

* Fix vit arch assertion

* Remove useless init function

* Add unit tests.

* Fix resize_pos_embed for DeiT

* Improve according to comments.
2021-12-15 22:44:57 +08:00
Ma Zerun 6f25bebe42
[Docs] Update docs. (#600)
* [Docs] The template provides united Docs and OpenMMLab drop-lists in
banner. Remove them from our `conf.py`.

* Move docs of different languages to the same folder
2021-12-15 10:34:34 +08:00
Ma Zerun 894a82ea4f
[Refactor] Change `load_json_logs` to `load_json_log`. (#602) 2021-12-14 18:03:27 +08:00
Ma Zerun c7c5ab7a04
[Dev] Update benchmark regression tools (#556)
* Update benchmark tools

* Fix AccessDeniedError

* Support to calculate flops and params with benchmark_valid.py

* Fix typo
2021-12-14 17:19:32 +08:00
mzr1996 e57b8cb33b [Fix] Fix docs generation. 2021-12-14 16:23:56 +08:00
mzr1996 5078869b4b [Fix] Fix cal_acc bug caused by the return type of accuracy. 2021-12-14 16:21:25 +08:00
Ma Zerun e3cf1881bb
[Enhance] Imporve efficiency of precision, recall, f1_score and support. (#595)
* [Enhance] Imporve efficiency of precision, recall, f1_score and support.

* Fix bugs

* Use np.maximum since torch doesn't have maximum before torch 1.7

* Fix bug
2021-12-13 17:24:59 +08:00
Zhicheng Chen 851b438574
[Feature] Support LAMB optimizer. (#591)
* impl lamb

* Add unit tests

* Fix unit test

* Fix unit tests

* Use list instead of tuple in `__all__` according to PEP8

Co-authored-by: mzr1996 <mzr1996@163.com>
2021-12-13 17:24:44 +08:00
Ma Zerun 188aa6ed5d
[Enhance] Improve accuracy calculation performance. (#592)
* Imporve accuracy calculate performance.

* Add unit tests for accuracy

* Reuse state_inds
2021-12-09 14:06:08 +08:00