Mmaction2

**Highlights**

- Support TorchServe
- Add video structuralize demo
- Support using 3D skeletons for skeleton-based action recognition
- Benchmark PoseC3D on UCF and HMDB

**New Features**

- Support TorchServe ([1212](https://github.com/open-mmlab/mmaction2/pull/1212))
- Support 3D skeletons pre-processing ([1218](https://github.com/open-mmlab/mmaction2/pull/1218))
- Support video structuralize demo ([1197](https://github.com/open-mmlab/mmaction2/pull/1197))

**Documentations**

- Revise README.md and add projects.md ([1214](https://github.com/open-mmlab/mmaction2/pull/1214))
- Add CN docs for Skeleton dataset, PoseC3D and ST-GCN ([1228](https://github.com/open-mmlab/mmaction2/pull/1228), [#1237](https://github.com/open-mmlab/mmaction2/pull/1237), [#1236](https://github.com/open-mmlab/mmaction2/pull/1236))
- Add tutorial for custom dataset training for skeleton-based action recognition ([1234](https://github.com/open-mmlab/mmaction2/pull/1234))

**Bug and Typo Fixes**

- Fix tutorial link ([1219](https://github.com/open-mmlab/mmaction2/pull/1219))
- Fix GYM links ([1224](https://github.com/open-mmlab/mmaction2/pull/1224))

**ModelZoo**

- Benchmark PoseC3D on UCF and HMDB ([1223](https://github.com/open-mmlab/mmaction2/pull/1223))
- Add ST-GCN + 3D skeleton model for NTU60-XSub ([1236](https://github.com/open-mmlab/mmaction2/pull/1236))

New Contributors
* bit-scientist made their first contribution in https://github.com/open-mmlab/mmaction2/pull/1234

**Full Changelog**: https://github.com/open-mmlab/mmaction2/compare/v0.19.0...v0.20.0

**Highlights**

- Support ST-GCN
- Refactor the inference API
- Add code spell check hook

**New Features**

- Support ST-GCN ([1123](https://github.com/open-mmlab/mmaction2/pull/1123))

**Improvement**

- Add label maps for every dataset ([1127](https://github.com/open-mmlab/mmaction2/pull/1127))
- Remove useless code MultiGroupCrop ([1180](https://github.com/open-mmlab/mmaction2/pull/1180))
- Refactor Inference API ([1191](https://github.com/open-mmlab/mmaction2/pull/1191))
- Add code spell check hook ([1208](https://github.com/open-mmlab/mmaction2/pull/1208))
- Use docker in CI ([1159](https://github.com/open-mmlab/mmaction2/pull/1159))

**Documentations**

- Update metafiles to new OpenMMLAB protocols ([1134](https://github.com/open-mmlab/mmaction2/pull/1134))
- Switch to new doc style ([1160](https://github.com/open-mmlab/mmaction2/pull/1160))
- Improve the ERROR message ([1203](https://github.com/open-mmlab/mmaction2/pull/1203))
- Fix invalid URL in getting_started ([1169](https://github.com/open-mmlab/mmaction2/pull/1169))

**Bug and Typo Fixes**

- Compatible with new MMClassification ([1139](https://github.com/open-mmlab/mmaction2/pull/1139))
- Add missing runtime dependencies ([1144](https://github.com/open-mmlab/mmaction2/pull/1144))
- Fix THUMOS tag proposals path ([1156](https://github.com/open-mmlab/mmaction2/pull/1156))
- Fix LoadHVULabel ([1194](https://github.com/open-mmlab/mmaction2/pull/1194))
- Switch the default value of `persistent_workers` to False ([1202](https://github.com/open-mmlab/mmaction2/pull/1202))
- Fix `_freeze_stages` for MobileNetV2 ([1193](https://github.com/open-mmlab/mmaction2/pull/1193))
- Fix resume when building rawframes ([1150](https://github.com/open-mmlab/mmaction2/pull/1150))
- Fix device bug for class weight ([1188](https://github.com/open-mmlab/mmaction2/pull/1188))
- Correct Arg names in extract_audio.py ([1148](https://github.com/open-mmlab/mmaction2/pull/1148))

**ModelZoo**

- Add TSM-MobileNetV2 ported from TSM ([1163](https://github.com/open-mmlab/mmaction2/pull/1163))
- Add ST-GCN for NTURGB+D-XSub-60 ([1123](https://github.com/open-mmlab/mmaction2/pull/1123))

**Improvement**

- Add CopyRight ([1099](https://github.com/open-mmlab/mmaction2/pull/1099))
- Support NTU Pose Extraction ([1076](https://github.com/open-mmlab/mmaction2/pull/1076))
- Support Caching in RawFrameDecode ([1078](https://github.com/open-mmlab/mmaction2/pull/1078))
- Add citations & Support python3.9 CI & Use fixed-version sphinx ([1125](https://github.com/open-mmlab/mmaction2/pull/1125))

**Documentations**

- Add Descriptions of PoseC3D dataset ([1053](https://github.com/open-mmlab/mmaction2/pull/1053))

**Bug and Typo Fixes**

- Fix SSV2 checkpoints ([1101](https://github.com/open-mmlab/mmaction2/pull/1101))
- Fix CSN normalization ([1116](https://github.com/open-mmlab/mmaction2/pull/1116))
- Fix typo ([1121](https://github.com/open-mmlab/mmaction2/pull/1121))
- Fix new_crop_quadruple bug ([1108](https://github.com/open-mmlab/mmaction2/pull/1108))

**Highlights**

- Support PyTorch 1.9
- Support Pytorchvideo Transforms
- Support PreciseBN

**New Features**

- Support Pytorchvideo Transforms ([1008](https://github.com/open-mmlab/mmaction2/pull/1008))
- Support PreciseBN ([1038](https://github.com/open-mmlab/mmaction2/pull/1038))

**Improvements**

- Remove redundant augmentations in config files ([996](https://github.com/open-mmlab/mmaction2/pull/996))
- Make resource directory to hold common resource pictures ([1011](https://github.com/open-mmlab/mmaction2/pull/1011))
- Remove deperecated FrameSelector ([1010](https://github.com/open-mmlab/mmaction2/pull/1010))
- Support Concat Dataset ([1000](https://github.com/open-mmlab/mmaction2/pull/1000))
- Add `to-mp4` option to resize_videos.py ([1021](https://github.com/open-mmlab/mmaction2/pull/1021))
- Add option to keep tail frames ([1050](https://github.com/open-mmlab/mmaction2/pull/1050))
- Update MIM support ([1061](https://github.com/open-mmlab/mmaction2/pull/1061))
- Calculate Top-K accurate and inaccurate classes ([1047](https://github.com/open-mmlab/mmaction2/pull/1047))

**Bug and Typo Fixes**

- Fix bug in PoseC3D demo ([1009](https://github.com/open-mmlab/mmaction2/pull/1009))
- Fix some problems in resize_videos.py ([1012](https://github.com/open-mmlab/mmaction2/pull/1012))
- Support torch1.9 ([1015](https://github.com/open-mmlab/mmaction2/pull/1015))
- Remove redundant code in CI ([1046](https://github.com/open-mmlab/mmaction2/pull/1046))
- Fix bug about persistent_workers ([1044](https://github.com/open-mmlab/mmaction2/pull/1044))
- Support TimeSformer feature extraction ([1035](https://github.com/open-mmlab/mmaction2/pull/1035))
- Fix ColorJitter ([1025](https://github.com/open-mmlab/mmaction2/pull/1025))

**ModelZoo**

- Add TSM-R50 sthv1 models trained by PytorchVideo RandAugment and AugMix ([1008](https://github.com/open-mmlab/mmaction2/pull/1008))
- Update SlowOnly SthV1 checkpoints ([1034](https://github.com/open-mmlab/mmaction2/pull/1034))
- Add SlowOnly Kinetics400 checkpoints trained with Precise-BN ([1038](https://github.com/open-mmlab/mmaction2/pull/1038))
- Add CSN-R50 from scratch checkpoints ([1045](https://github.com/open-mmlab/mmaction2/pull/1045))
- TPN Kinetics-400 Checkpoints trained with the new ColorJitter ([1025](https://github.com/open-mmlab/mmaction2/pull/1025))

**Documentation**

- Add Chinese translation of feature_extraction.md ([1020](https://github.com/open-mmlab/mmaction2/pull/1020))
- Fix the code snippet in getting_started.md ([1023](https://github.com/open-mmlab/mmaction2/pull/1023))
- Fix TANet config table ([1028](https://github.com/open-mmlab/mmaction2/pull/1028))
- Add description to PoseC3D dataset ([1053](https://github.com/open-mmlab/mmaction2/pull/1053))

**Highlights**

- Support using backbone from pytorch-image-models(timm)
- Support PIMS Decoder
- Demo for skeleton-based action recognition
- Support Timesformer

**New Features**

- Support using backbones from pytorch-image-models(timm) for TSN ([880](https://github.com/open-mmlab/mmaction2/pull/880))
- Support torchvision transformations in preprocessing pipelines ([972](https://github.com/open-mmlab/mmaction2/pull/972))
- Demo for skeleton-based action recognition ([972](https://github.com/open-mmlab/mmaction2/pull/972))
- Support Timesformer ([839](https://github.com/open-mmlab/mmaction2/pull/839))

**Improvements**

- Add a tool to find invalid videos ([907](https://github.com/open-mmlab/mmaction2/pull/907), [#950](https://github.com/open-mmlab/mmaction2/pull/950))
- Add an option to specify spectrogram_type ([909](https://github.com/open-mmlab/mmaction2/pull/909))
- Add json output to video demo ([906](https://github.com/open-mmlab/mmaction2/pull/906))
- Add MIM related docs ([918](https://github.com/open-mmlab/mmaction2/pull/918))
- Rename lr to scheduler ([916](https://github.com/open-mmlab/mmaction2/pull/916))
- Support `--cfg-options` for demos ([911](https://github.com/open-mmlab/mmaction2/pull/911))
- Support number counting for flow-wise filename template ([922](https://github.com/open-mmlab/mmaction2/pull/922))
- Add Chinese tutorial ([941](https://github.com/open-mmlab/mmaction2/pull/941))
- Change ResNet3D default values ([939](https://github.com/open-mmlab/mmaction2/pull/939))
- Adjust script structure ([935](https://github.com/open-mmlab/mmaction2/pull/935))
- Add font color to args in long_video_demo ([947](https://github.com/open-mmlab/mmaction2/pull/947))
- Polish code style with Pylint ([908](https://github.com/open-mmlab/mmaction2/pull/908))
- Support PIMS Decoder ([946](https://github.com/open-mmlab/mmaction2/pull/946))
- Improve Metafiles ([956](https://github.com/open-mmlab/mmaction2/pull/956), [#979](https://github.com/open-mmlab/mmaction2/pull/979), [#966](https://github.com/open-mmlab/mmaction2/pull/966))
- Add links to download Kinetics400 validation ([920](https://github.com/open-mmlab/mmaction2/pull/920))
- Audit the usage of shutil.rmtree ([943](https://github.com/open-mmlab/mmaction2/pull/943))
- Polish localizer related codes([913](https://github.com/open-mmlab/mmaction2/pull/913))

**Bug and Typo Fixes**

- Fix spatiotemporal detection demo ([899](https://github.com/open-mmlab/mmaction2/pull/899))
- Fix docstring for 3D inflate ([925](https://github.com/open-mmlab/mmaction2/pull/925))
- Fix bug of writing text to video with TextClip ([952](https://github.com/open-mmlab/mmaction2/pull/952))
- Fix mmcv install in CI ([977](https://github.com/open-mmlab/mmaction2/pull/977))

**ModelZoo**

- Add TSN with Swin Transformer backbone as an example for using pytorch-image-models(timm) backbones ([880](https://github.com/open-mmlab/mmaction2/pull/880))
- Port CSN checkpoints from VMZ ([945](https://github.com/open-mmlab/mmaction2/pull/945))
- Release various checkpoints for UCF101, HMDB51 and Sthv1 ([938](https://github.com/open-mmlab/mmaction2/pull/938))
- Support Timesformer ([839](https://github.com/open-mmlab/mmaction2/pull/839))
- Update TSM modelzoo ([981](https://github.com/open-mmlab/mmaction2/pull/981))

**Highlights**

- Support PoseC3D
- Support ACRN
- Support MIM

**New Features**

- Support PoseC3D ([786](https://github.com/open-mmlab/mmaction2/pull/786), [#890](https://github.com/open-mmlab/mmaction2/pull/890))
- Support MIM ([870](https://github.com/open-mmlab/mmaction2/pull/870))
- Support ACRN and Focal Loss ([891](https://github.com/open-mmlab/mmaction2/pull/891))
- Support Jester dataset ([864](https://github.com/open-mmlab/mmaction2/pull/864))

**Improvements**

- Add `metric_options` for evaluation to docs ([873](https://github.com/open-mmlab/mmaction2/pull/873))
- Support creating a new label map based on custom classes for demos about spatio temporal demo ([879](https://github.com/open-mmlab/mmaction2/pull/879))
- Improve document about AVA dataset preparation ([878](https://github.com/open-mmlab/mmaction2/pull/878))
- Provide a script to extract clip-level feature ([856](https://github.com/open-mmlab/mmaction2/pull/856))

**Bug and Typo Fixes**

- Fix issues about resume ([877](https://github.com/open-mmlab/mmaction2/pull/877), [#878](https://github.com/open-mmlab/mmaction2/pull/878))
- Correct the key name of `eval_results` dictionary for metric 'mmit_mean_average_precision' ([885](https://github.com/open-mmlab/mmaction2/pull/885))

**ModelZoo**

- Support Jester dataset ([864](https://github.com/open-mmlab/mmaction2/pull/864))
- Support ACRN and Focal Loss ([891](https://github.com/open-mmlab/mmaction2/pull/891))