MMAction2 V0.22.0 Release

0.22.0 (03/05/2022)

Highlights

• Support Multigrid training strategy
• Support CPU training
• Support audio demo
• Support topk customizing in models/heads/base.py

New Features

• Support Multigrid training strategy(#1378)
• Support STGCN in demo_skeleton.py(#1391)
• Support CPU training(#1407)
• Support audio demo(#1425)
• Support topk customizing in models/heads/base.py(#1452)

Documentations

• Add OpenMMLab platform(#1393)
• Update links(#1394)
• Update readme in configs(#1404)
• Update instructions to install mmcv-full(#1426)
• Add shortcut(#1433)
• Update modelzoo(#1439)
• add video_structuralize in readme(#1455)
• Update OpenMMLab repo information(#1482)

Bug and Typo Fixes

• Update train.py(#1375)
• Fix printout bug(#1382)
• Update multi processing setting(#1395)
• Setup multi processing both in train and test(#1405)
• Fix bug in nondistributed multi-gpu training(#1406)
• Add variable fps in ava_dataset.py(#1409)
• Only support distributed training(#1414)
• Set test_mode for AVA configs(#1432)
• Support single label(#1434)
• Add check copyright(#1447)
• Support Windows CI(#1448)
• Fix wrong device of class_weight in models/losses/cross_entropy_loss.py(#1457)
• Fix bug caused by distributed(#1459)
• Update readme(#1460)
• Fix lint caused by colab automatic upload(#1461)
• Refine CI(#1471)
• Update pre-commit(#1474)
• Add deprecation message for deploy tool(#1483)

ModelZoo

• Support slowfast_steplr(#1421)

MMAction2 V0.21.0 Release

Highlights

• Support 2s-AGCN
• Support publish models in Windows
• Improve some sthv1 related models
• Support BABEL

New Features

• Support 2s-AGCN(#1248)
• Support skip postproc in ntu_pose_extraction(#1295)
• Support publish models in Windows(#1325)
• Add copyright checkhook in pre-commit-config(#1344)

Documentations

• Add MMFlow (#1273)
• Revise README.md and add projects.md (#1286)
• Add 2s-AGCN in Updates(#1289)
• Add MMFewShot(#1300)
• Add MMHuman3d(#1304)
• Update pre-commit(#1313)
• Use share menu from the theme instead(#1328)
• Update installation command(#1340)

Bug and Typo Fixes

• Update the inference part in notebooks(#1256)
• Update the map_location(#1262)
• Fix bug that start_index is not used in RawFrameDecode(#1278)
• Fix bug in init_random_seed(#1282)
• Fix bug in setup.py(#1303)
• Fix interrogate error in workflows(#1305)
• Fix typo in slowfast config(#1309)
• Cancel previous runs that are not completed(#1327)
• Fix missing skip_postproc parameter(#1347)
• Update ssn.py(#1355)
• Use latest youtube-dl(#1357)
• Fix test-best(#1362)

ModelZoo

• Improve some sthv1 related models(#1306)
• Support BABEL(#1332)

MMAction2 V0.20.0 Release

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)
• Support 3D skeletons pre-processing (#1218)
• Support video structuralize demo (#1197)

Documentations

• Revise README.md and add projects.md (#1214)
• Add CN docs for Skeleton dataset, PoseC3D and ST-GCN (#1228, #1237, #1236)
• Add tutorial for custom dataset training for skeleton-based action recognition (#1234)

Bug and Typo Fixes

• Fix tutorial link (#1219)
• Fix GYM links (#1224)

ModelZoo

• Benchmark PoseC3D on UCF and HMDB (#1223)
• Add ST-GCN + 3D skeleton model for NTU60-XSub (#1236)

New Contributors

• @bit-scientist made their first contribution in #1234

Full Changelog: v0.19.0...v0.20.0

MMAction2 V0.19.0 Release

Highlights

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

New Features

• Support ST-GCN (#1123)

Improvement

• Add label maps for every dataset (#1127)
• Remove useless code MultiGroupCrop (#1180)
• Refactor Inference API (#1191)
• Add code spell check hook (#1208)
• Use docker in CI (#1159)

Documentations

• Update metafiles to new OpenMMLAB protocols (#1134)
• Switch to new doc style (#1160)
• Improve the ERROR message (#1203)
• Fix invalid URL in getting_started (#1169)

Bug and Typo Fixes

• Compatible with new MMClassification (#1139)
• Add missing runtime dependencies (#1144)
• Fix THUMOS tag proposals path (#1156)
• Fix LoadHVULabel (#1194)
• Switch the default value of persistent_workers to False (#1202)
• Fix _freeze_stages for MobileNetV2 (#1193)
• Fix resume when building rawframes (#1150)
• Fix device bug for class weight (#1188)
• Correct Arg names in extract_audio.py (#1148)

ModelZoo

• Add TSM-MobileNetV2 ported from TSM (#1163)
• Add ST-GCN for NTURGB+D-XSub-60 (#1123)

MMAction2 V0.18.0 Release

Improvement

• Add CopyRight (#1099)
• Support NTU Pose Extraction (#1076)
• Support Caching in RawFrameDecode (#1078)
• Add citations & Support python3.9 CI & Use fixed-version sphinx (#1125)

Documentations

• Add Descriptions of PoseC3D dataset (#1053)

Bug and Typo Fixes

• Fix SSV2 checkpoints (#1101)
• Fix CSN normalization (#1116)
• Fix typo (#1121)
• Fix new_crop_quadruple bug (#1108)

MMAction2 V0.17.0 Release

Highlights

• Support PyTorch 1.9
• Support Pytorchvideo Transforms
• Support PreciseBN

New Features

• Support Pytorchvideo Transforms (#1008)
• Support PreciseBN (#1038)

Improvements

• Remove redundant augmentations in config files (#996)
• Make resource directory to hold common resource pictures (#1011)
• Remove deperecated FrameSelector (#1010)
• Support Concat Dataset (#1000)
• Add to-mp4 option to resize_videos.py (#1021)
• Add option to keep tail frames (#1050)
• Update MIM support (#1061)
• Calculate Top-K accurate and inaccurate classes (#1047)

Bug and Typo Fixes

• Fix bug in PoseC3D demo (#1009)
• Fix some problems in resize_videos.py (#1012)
• Support torch1.9 (#1015)
• Remove redundant code in CI (#1046)
• Fix bug about persistent_workers (#1044)
• Support TimeSformer feature extraction (#1035)
• Fix ColorJitter (#1025)

ModelZoo

• Add TSM-R50 sthv1 models trained by PytorchVideo RandAugment and AugMix (#1008)
• Update SlowOnly SthV1 checkpoints (#1034)
• Add SlowOnly Kinetics400 checkpoints trained with Precise-BN (#1038)
• Add CSN-R50 from scratch checkpoints (#1045)
• TPN Kinetics-400 Checkpoints trained with the new ColorJitter (#1025)

Documentation

• Add Chinese translation of feature_extraction.md (#1020)
• Fix the code snippet in getting_started.md (#1023)
• Fix TANet config table (#1028)
• Add description to PoseC3D dataset (#1053)

MMAction2 V0.16.0 Release

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)
• Support torchvision transformations in preprocessing pipelines (#972)
• Demo for skeleton-based action recognition (#972)
• Support Timesformer (#839)

Improvements

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

Bug and Typo Fixes

• Fix spatiotemporal detection demo (#899)
• Fix docstring for 3D inflate (#925)
• Fix bug of writing text to video with TextClip (#952)
• Fix mmcv install in CI (#977)

ModelZoo

• Add TSN with Swin Transformer backbone as an example for using pytorch-image-models(timm) backbones (#880)
• Port CSN checkpoints from VMZ (#945)
• Release various checkpoints for UCF101, HMDB51 and Sthv1 (#938)
• Support Timesformer (#839)
• Update TSM modelzoo (#981)

MMAction2 V0.15.0 Release

Highlights

• Support PoseC3D
• Support ACRN
• Support MIM

New Features

• Support PoseC3D (#786, #890)
• Support MIM (#870)
• Support ACRN and Focal Loss (#891)
• Support Jester dataset (#864)

Improvements

• Add metric_options for evaluation to docs (#873)
• Support creating a new label map based on custom classes for demos about spatio temporal demo (#879)
• Improve document about AVA dataset preparation (#878)
• Provide a script to extract clip-level feature (#856)

Bug and Typo Fixes

• Fix issues about resume (#877, #878)
• Correct the key name of eval_results dictionary for metric 'mmit_mean_average_precision' (#885)

ModelZoo

• Support Jester dataset (#864)
• Support ACRN and Focal Loss (#891)

MMAction2 V0.14.0 Release

Highlights

• Support TRN
• Support Diving48

New Features

• Support TRN (#755)
• Support Diving48 (#835)
• Support Webcam Demo for Spatio-temporal Action Detection Models (#795)

Improvements

• Add softmax option for pytorch2onnx tool (#781)
• Support TRN (#755)
• Test with onnx models and TensorRT engines (#758)
• Speed up AVA Testing (#784)
• Add self.with_neck attribute (#796)
• Update installation document (#798)
• Use a random master port (#809)
• Update AVA processing data document (#801)
• Refactor spatio-temporal augmentation (#782)
• Add QR code in CN README (#812)
• Add Alternative way to download Kinetics (#817, #822)
• Refactor Sampler (#790)
• Use EvalHook in MMCV with backward compatibility (#793)
• Use MMCV Model Registry (#843)

Bug and Typo Fixes

• Fix a bug in pytorch2onnx.py when num_classes <= 4 (#800, #824)
• Fix demo_spatiotemporal_det.py error (#803, #805)
• Fix loading config bugs when resume (#820)
• Make HMDB51 annotation generation more robust (#811)

ModelZoo

• Update checkpoint for 256 height in something-V2 (#789)
• Support Diving48 (#835)

MMAction2 V0.13.0 Release

Highlights

• Support LFB
• Support using backbone from MMCls/TorchVision
• Add Chinese documentation

New Features

• Support LFB (#553)
• Support using backbones from MMCls for TSN (#679)
• Support using backbones from TorchVision for TSN (#720)
• Support Mixup and Cutmix for recognizers (#681)
• Support Chinese documentation (#665, #680, #689, #701, #702, #703, #706, #716, #717, #731, #733, #735, #736, #737, #738, #739, #740, #742, #752, #759, #761, #772, #775)

Improvements

• Add slowfast config/json/log/ckpt for training custom classes of AVA (#678)
• Set RandAugment as Imgaug default transforms (#585)
• Add --test-last & --test-best for tools/train.py to test checkpoints after training (#608)
• Add fcn_testing in TPN (#684)
• Remove redundant recall functions (#741)
• Recursively remove pretrained step for testing (#695)
• Improve demo by limiting inference fps (#668)

Bug and Typo Fixes

• Fix a bug about multi-class in VideoDataset (#723)
• Reverse key-value in anet filelist generation (#686)
• Fix flow norm cfg typo (#693)

ModelZoo

• Add LFB for AVA2.1 (#553)
• Add TSN with ResNeXt-101-32x4d backbone as an example for using MMCls backbones (#679)
• Add TSN with Densenet161 backbone as an example for using TorchVision backbones (#720)
• Add slowonly_nl_embedded_gaussian_r50_4x16x1_150e_kinetics400_rgb (#690)
• Add slowonly_nl_embedded_gaussian_r50_8x8x1_150e_kinetics400_rgb (#704)
• Add slowonly_nl_kinetics_pretrained_r50_4x16x1(8x8x1)_20e_ava_rgb (#730)