MMPose V0.28.1 Release

This release is meant to fix the compatibility with the latest mmcv v1.6.1

MMPose V0.28.0 Release

Highlights

• Support TCFormer backbone, CVPR'2022 (#1447, #1452) @zengwang430521
• Add RLE models on COCO dataset (#1424) @Indigo6, @Ben-Louis, @ly015
• Update swin models with better performance (#1467) @jin-s13

New Features

• Support TCFormer backbone, CVPR'2022 (#1447, #1452) @zengwang430521
• Add RLE models on COCO dataset (#1424) @Indigo6, @Ben-Louis, @ly015
• Support layer decay optimizer conctructor and learning rate decay optimizer constructor (#1423) @jin-s13

Improvements

• Improve documentation quality (#1416, #1421, #1423, #1426, #1458, #1463) @ly015, @liqikai9
• Support installation by mim (#1425) @liqikai9
• Support PAVI logger (#1434) @EvelynWang-0423
• Add progress bar for some demos (#1454) @liqikai9
• Webcam API supports quick device setting in terminal commands (#1466) @ly015
• Update swin models with better performance (#1467) @jin-s13

Bug Fixes

• Rename custom_hooks_config to custom_hooks in configs to align with the documentation (#1427) @ly015
• Fix deadlock issue in Webcam API (#1430) @ly015
• Fix smoother configs in video 3D demo (#1457) @ly015

MMPose V0.27.0 Release

Highlights

• Support hand gesture recognition
  • Try the demo for gesture recognition
  • Learn more about the algorithm, dataset and experiment results
• Major upgrade to the Webcam API
  • Tutorials (EN|zh_CN)
  • API Reference
  • Demo

New Features

• Support gesture recognition algorithm MTUT CVPR'2019 and dataset NVGesture CVPR'2016 (#1380) @Ben-Louis

Improvements

• Upgrade Webcam API and related documents (#1393, #1404, #1413) @ly015
• Support exporting COCO inference result without the annotation file (#1368) @liqikai9
• Replace markdownlint with mdformat in CI to avoid the dependence on ruby #1382 @ly015
• Improve documentation quality (#1385, #1394, #1395, #1408) @chubei-oppen, @ly015, @liqikai9

Bug Fixes

• Fix xywh->xyxy bbox conversion in dataset sanity check (#1367) @jin-s13
• Fix a bug in two-stage 3D keypoint demo (#1373) @ly015
• Fix out-dated settings in PVT configs (#1376) @ly015
• Fix myst settings for document compiling (#1381) @ly015
• Fix a bug in bbox transform (#1384) @ly015
• Fix inaccurate description of min_keypoints in tracking apis (#1398) @pallgeuer
• Fix warning with torch.meshgrid (#1402) @pallgeuer
• Remove redundant transformer modules from mmpose.datasets.backbones.utils (#1405) @ly015

MMPose V0.26.0 Release

Highlights

• Support RLE (Residual Log-likelihood Estimation), ICCV'2021 (#1259) @Indigo6, @ly015
• Support Swin Transformer, ICCV'2021 (#1300) @yumendecc, @ly015
• Support PVT, ICCV'2021 and PVTv2, CVMJ'2022 (#1343) @zengwang430521
• Speed up inference and reduce CPU usage by optimizing the pre-processing pipeline (#1320) @chenxinfeng4, @liqikai9

New Features

• Support RLE (Residual Log-likelihood Estimation), ICCV'2021 (#1259) @Indigo6, @ly015
• Support Swin Transformer, ICCV'2021 (#1300) @yumendecc, @ly015
• Support PVT, ICCV'2021 and PVTv2, CVMJ'2022 (#1343) @zengwang430521
• Support FPN, CVPR'2017 (#1300) @yumendecc, @ly015

Improvements

• Speed up inference and reduce CPU usage by optimizing the pre-processing pipeline (#1320) @chenxinfeng4, @liqikai9
• Video demo supports models that requires multi-frame inputs (#1300) @liqikai9, @jin-s13
• Update benchmark regression list (#1328) @ly015, @liqikai9
• Remove unnecessary warnings in TopDownPoseTrack18VideoDataset (#1335) @liqikai9
• Improve documentation quality (#1313, #1305) @Ben-Louis, @ly015
• Update deprecating settings in configs (#1317) @ly015

Bug Fixes

• Fix a bug in human skeleton grouping that may skip the matching process unexpectedly when ignore_to_much is True (#1341) @daixinghome
• Fix a GPG key error that leads to CI failure (#1354) @ly015
• Fix bugs in distributed training script (#1338, #1298) @ly015
• Fix an upstream bug in xtoccotools that causes incorrect AP(M) results (#1308) @jin-s13, @ly015
• Fix indentiation errors in the colab tutorial (#1298) @YuanZi1501040205
• Fix incompatible model weight initialization with other OpenMMLab codebases (#1329) @274869388
• Fix HRNet FP16 checkpoints download URL (#1309) @YinAoXiong
• Fix typos in body3d_two_stage_video_demo.py (#1295) @mucozcan

Breaking Changes

• Refactor bbox processing in datasets and pipelines (#1311) @ly015, @Ben-Louis
  The bbox format conversion (xywh to center-scale) and random translation are moved from the dataset to the pipeline. The comparison between new and old version is as below:

	v0.26.0	v0.25.0
Dataset (e.g. TopDownCOCODataset)	... # Data sample only contains bbox rec.append({ 'bbox': obj['clean_bbox][:4], ... })	... # Convert bbox from xywh to center-scale center, scale = self._xywh2cs(*obj['clean_bbox'][:4]) # Data sample contains center and scale rec.append({ 'bbox': obj['clean_bbox][:4], 'center': center, 'scale': scale, ... })
Pipeline Config (e.g. HRNet+COCO)	... train_pipeline = [ dict(type='LoadImageFromFile'), # Convert bbox from xywh to center-scale dict(type='TopDownGetBboxCenterScale', padding=1.25), # Randomly shift bbox center dict(type='TopDownRandomShiftBboxCenter', shift_factor=0.16, prob=0.3), ... ]	... train_pipeline = [ dict(type='LoadImageFromFile'), ... ]
Advantage	Simpler data sample content Flexible bbox format conversion and augmentation Apply bbox random translation every epoch (instead of only applying once at the annotation loading)	-
BC Breaking	The method _xywh2cs of dataset base classes (e.g. Kpt2dSviewRgbImgTopDownDataset) will be deprecated in the future. Custom datasets will need modifications to move the bbox format conversion to pipelines.	-

MMPose V0.25.1 Release

This release is meant to fix the compatibility with the latest mmcv v1.5.0

MMPose V0.25.0 Release

Highlights

• Support Shelf and Campus datasets with pre-trained VoxelPose models, "3D Pictorial Structures for Multiple Human Pose Estimation", CVPR'2014 (#1225) @liqikai9 @wusize
• Add Smoother module for temporal smoothing of the pose estimation with configurable filters (#1127) @ailingzengzzz, @ly015
• Support SmoothNet for pose smoothing, "SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos", arXiv'2021 (#1279) @ailingzengzzz, @ly015
• Add multiview 3D pose estimation demo (#1270) @wusize

New Features

• Support Shelf and Campus datasets with pre-trained VoxelPose models, "3D Pictorial Structures for Multiple Human Pose Estimation", CVPR'2014 (#1225) @liqikai9 @wusize
• Add Smoother module for temporal smoothing of the pose estimation with configurable filters (#1127) @ailingzengzzz, @ly015
• Support SmoothNet for pose smoothing, "SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos", arXiv'2021 (#1279) @ailingzengzzz, @ly015
• Add multiview 3D pose estimation demo (#1270) @wusize
• Support multi-machine distributed training (#1248) @ly015

Improvements

• Update HRFormer configs and checkpoints with relative position bias (#1245) @zengwang430521
• Support using different random seed for each distributed node (#1257, #1229) @ly015
• Improve documentation quality (#1275, #1255, #1258, #1249, #1247, #1240, #1235) @ly015, @jin-s13, @YoniChechik

Bug Fixes

• Fix keypoint index in RHD dataset meta information (#1265) @liqikai9
• Fix pre-commit hook unexpected behavior on Windows (#1282) @liqikai9
• Remove python-dev installation in CI (#1276) @ly015
• Unify hyphens in argument names in tools and demos (#1271) @ly015
• Fix ambiguous channel size in channel_shuffle that may cause exporting failure (#1242) @PINTO0309
• Fix a bug in Webcam API that causes single-class detectors fail (#1239) @674106399
• Fix the issue that custom_hook can not be set in configs (#1236) @bladrome
• Fix incompatible MMCV version in DockerFile (#raykindle)
• Skip invisible joints in visualization (#1228) @womeier

MMPose V0.24.0 Release

Highlights

• Support HRFormer "HRFormer: High-Resolution Vision Transformer for Dense Predict", NeurIPS'2021 (#1203) @zengwang430521
• Support Windows installation with pip (#1213) @jin-s13, @ly015
• Add WebcamAPI documents and tutorials (#1187) @ly015

New Features

• Support HRFormer "HRFormer: High-Resolution Vision Transformer for Dense Predict", NeurIPS'2021 (#1203) @zengwang430521
• Support Windows installation with pip (#1213) @jin-s13, @ly015
• Support CPU training with mmcv < v1.4.4 (#1161) @EasonQYS, @ly015
• Add "Valentine Magic" demo with WebcamAPI (#1189, #1191) @liqikai9

Improvements

• Refactor multi-view 3D pose estimation framework towards better modularization and expansibility (#1196) @wusize
• Add WebcamAPI documents and tutorials (#1187) @ly015
• Refactor dataset evaluation interface to align with other OpenMMLab codebases (#1209) @ly015
• Add deprecation message for deploy tools since MMDeploy has supported MMPose (#1207) @QwQ2000
• Improve documentation quality (#1206, #1161) @ly015
• Switch to OpenMMLab official pre-commit-hook for copyright check (#1214) @ly015

Bug Fixes

• Fix hard-coded data collating and scattering in inference (#1175) @ly015
• Fix model configs on JHMDB dataset (#1188) @jin-s13
• Fix area calculation in pose tracking inference (#1197) @pallgeuer
• Fix registry scope conflict of module wrapper (#1204) @ly015
• Update MMCV installation in CI and documents (#1205)
• Fix incorrect color channel order in visualization functions (#1212) @ly015

MMPose V0.23.0 Release

Highlights

• Add MMPose Webcam API: A simple yet powerful tools to develop interactive webcam applications with MMPose functions. (#1178, #1173, #1173, #1143, #1094, #1133, #1098, #1160) @ly015, @jin-s13, @liqikai9, @wusize, @luminxu, @zengwang430521 @mzr1996

New Features

• Add MMPose Webcam API: A simple yet powerful tools to develop interactive webcam applications with MMPose functions. (#1178, #1173, #1173, #1143, #1094, #1133, #1098, #1160) @ly015, @jin-s13, @liqikai9, @wusize, @luminxu, @zengwang430521 @mzr1996
• Support ConcatDataset (#1139) @Canwang-sjtu
• Support CPU training and testing (#1157) @ly015

Improvements

• Add multi-processing configurations to speed up distributed training and testing (#1146) @ly015

• Add default runtime config (#1145)

• Upgrade isort in pre-commit hook (#1179) @liqikai9

• Update README and documents (#1171, #1167, #1153, #1149, #1148, #1147, #1140) @jin-s13, @wusize, @TommyZihao, @ly015

Bug Fixes

• Fix undeterministic behavior in pre-commit hooks (#1136) @jin-s13
• Deprecate the support for "python setup.py test" (#1179) @ly015
• Fix incompatible settings with MMCV on HSigmoid default parameters (#1132) @ly015
• Fix albumentation installation (#1184) @BIGWangYuDong

MMPose V0.22.0 Release

Highlights

• Support VoxelPose "VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment", ECCV'2020 (#1050) @wusize
• Support Soft Wing loss "Structure-Coherent Deep Feature Learning for Robust Face Alignment", TIP'2021 (#1077) @jin-s13
• Support Adaptive Wing loss "Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression", ICCV'2019 (#1072) @jin-s13

New Features

• Support VoxelPose "VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment", ECCV'2020 (#1050) @wusize
• Support Soft Wing loss "Structure-Coherent Deep Feature Learning for Robust Face Alignment", TIP'2021 (#1077) @jin-s13
• Support Adaptive Wing loss "Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression", ICCV'2019 (#1072) @jin-s13
• Add LiteHRNet-18 Checkpoints trained on COCO. (#1120) @jin-s13

Improvements

• Improve documentation quality (#1115, #1111, #1105, #1087, #1086, #1085, #1084, #1083, #1124, #1070, #1068) @jin-s13, @liqikai9, @ly015
• Support CircleCI (#1074) @ly015
• Skip unit tests in CI when only document files were changed (#1074, #1041) @QwQ2000, @ly015
• Support file_client_args in LoadImageFromFile (#1076) @jin-s13

Bug Fixes

• Fix a bug in Dark UDP postprocessing that causes error when the channel number is large. (#1079, #1116) @X00123, @jin-s13
• Fix hard-coded sigmas in bottom-up image demo (#1107, #1101) @chenxinfeng4, @liqikai9
• Fix unstable checks in unit tests (#1112) @ly015
• Do not destroy NULL windows if args.show==False in demo scripts (#1104) @bladrome

MMPose V0.21.0 Release

Highlights

• Support "Learning Temporal Pose Estimation from Sparsely-Labeled Videos", NeurIPS'2019 (#932, #1006, #1036, #1060) @liqikai9
• Add ViPNAS-MobileNetV3 models (#1025) @luminxu, @jin-s13
• Add inference speed benchmark (#1028, #1034, #1044) @liqikai9

New Features

• Support "Learning Temporal Pose Estimation from Sparsely-Labeled Videos", NeurIPS'2019 (#932, #1006, #1036) @liqikai9
• Add ViPNAS-MobileNetV3 models (#1025) @luminxu, @jin-s13
• Add light-weight top-down models for whole-body keypoint detection (#1009, #1020, #1055) @luminxu, @ly015
• Add HRNet checkpoints with various settings on PoseTrack18 (#1035) @liqikai9

Improvements

• Add inference speed benchmark (#1028, #1034, #1044) @liqikai9
• Update model metafile format (#1001) @ly015
• Support minus output feature index in mobilenet_v3 (#1005) @luminxu
• Improve documentation quality (#1018, #1026, #1027, #1031, #1038, #1046, #1056, #1057) @edybk, @luminxu, @ly015, @jin-s13
• Set default random seed in training initialization (#1030) @ly015
• Skip CI when only specific files changed (#1041, #1059) @QwQ2000, @ly015
• Automatically cancel uncompleted action runs when new commit arrives (#1053) @ly015

Bug Fixes

• Update pose tracking demo to be compatible with latest mmtracking (#1014) @jin-s13
• Fix symlink creation failure when installed in Windows environments (#1039) @QwQ2000
• Fix AP-10K dataset sigmas (#1040) @jin-s13