MMPose V0.20.0 Release

Highlights

• Add AP-10K dataset for animal pose estimation (#987) @Annbless, @AlexTheBad, @jin-s13, @ly015
• Support TorchServe (#979) @ly015

New Features

• Add AP-10K dataset for animal pose estimation (#987) @Annbless, @AlexTheBad, @jin-s13, @ly015
• Add HRNetv2 checkpoints on 300W and COFW datasets (#980) @jin-s13
• Support TorchServe (#979) @ly015

Bug Fixes

• Fix some deprecated or risky settings in configs (#963, #976, #992) @jin-s13, @wusize
• Fix issues of default arguments of training and testing scripts (#970, #985) @liqikai9, @wusize
• Fix heatmap and tag size mismatch in bottom-up with UDP (#994) @wusize
• Fix python3.9 installation in CI (#983) @ly015
• Fix model zoo document integrity issue (#990) @jin-s13

Improvements

• Support non-square input shape for bottom-up (#991) @wusize
• Add image and video resources for demo (#971) @liqikai9
• Use CUDA docker images to accelerate CI (#973) @ly015
• Add codespell hook and fix detected typos (#977) @ly015

MMPose V0.19.0 Release

Highlights

• Add models for Associative Embedding with Hourglass network backbone (#906, #955) @jin-s13, @luminxu
• Support COCO-Wholebody-Face and COCO-Wholebody-Hand datasets (#813) @jin-s13, @innerlee, @luminxu
• Upgrade dataset interface (#901, #924) @jin-s13, @innerlee, @ly015, @liqikai9
• New style of documentation (#945) @ly015

New Features

• Add models for Associative Embedding with Hourglass network backbone (#906, #955) @jin-s13, @luminxu
• Support COCO-Wholebody-Face and COCO-Wholebody-Hand datasets (#813) @jin-s13, @innerlee, @luminxu
• Add pseudo-labeling tool to generate COCO style keypoint annotations with given bounding boxes (#928) @soltkreig
• New style of documentation (#945) @ly015

Bug Fixes

• Fix segmentation parsing in Macaque dataset preprocessing (#948) @jin-s13
• Fix dependencies that may lead to CI failure in downstream projects (#936, #953) @RangiLyu, @ly015
• Fix keypoint order in Human3.6M dataset (#940) @ttxskk
• Fix unstable image loading for Interhand2.6M (#913) @zengwang430521

Improvements

• Upgrade dataset interface (#901, #924) @jin-s13, @innerlee, @ly015, @liqikai9
• Improve demo usability and stability (#908, #934) @ly015
• Standardize model metafile format (#941) @ly015
• Support persistent_worker and several other arguments in configs (#946) @jin-s13
• Use MMCV root model registry to enable cross-project module building (#935) @RangiLyu
• Improve the document quality (#916, #909, #942, #913, #956) @jin-s13, @ly015, @bit-scientist, @zengwang430521
• Improve pull request template (#952, #954) @ly015

Breaking Changes

• Upgrade dataset interface (#901) @jin-s13, @innerlee, @ly015

MMPose V0.18.0 Release

Improvements

• Add automatic benchmark regression tools (#849, #880, #885) @liqikai9, @ly015
• Add copyright information and checking hook (#872)
• Add PR template (#875) @ly015
• Add citation information (#876) @ly015
• Add python3.9 in CI (#877, #883) @ly015
• Improve the quality of the documents (#845, #845, #848, #867, #870, #873, #896) @jin-s13, @ly015, @zhiqwang

Bug Fixes

• Fix redundant model weight loading in pytorch-to-onnx conversion (#850) @ly015
• Fix a bug in update_model_index.py that may cause pre-commit hook failure(#866) @ly015
• Fix a bug in interhand_3d_head (#890) @zengwang430521
• Fix pose tracking demo failure caused by out-of-date configs (#891)

MMPose V0.17.0 Release

Highlights

1. Support "Lite-HRNet: A Lightweight High-Resolution Network" CVPR'2021 (#733,#800) @jin-s13
2. Add 3d body mesh demo (#771) @zengwang430521
3. Add Chinese documentation (#787, #798, #799, #802, #804, #805, #815, #816, #817, #819, #839) @ly015, @luminxu, @jin-s13, @liqikai9, @zengwang430521
4. Add Colab Tutorial (#834) @ly015

New Features

• Support "Lite-HRNet: A Lightweight High-Resolution Network" CVPR'2021 (#733,#800) @jin-s13
• Add 3d body mesh demo (#771) @zengwang430521
• Add Chinese documentation (#787, #798, #799, #802, #804, #805, #815, #816, #817, #819, #839) @ly015, @luminxu, @jin-s13, @liqikai9, @zengwang430521
• Add Colab Tutorial (#834) @ly015
• Support training for InterHand v1.0 dataset (#761) @zengwang430521

Bug Fixes

• Fix mpii pckh@0.1 index (#773) @jin-s13
• Fix multi-node distributed test (#818) @ly015
• Fix docstring and init_weights error of ShuffleNetV1 (#814) @Junjun2016
• Fix imshow_bbox error when input bboxes is empty (#796) @ly015
• Fix model zoo doc generation (#778) @ly015
• Fix typo (#767), (#780, #782) @ly015, @jin-s13

Breaking Changes

• Use MMCV EvalHook (#686) @ly015

Improvements

• Add pytest.ini and fix docstring (#812) @jin-s13
• Support None as target weights in losses (#829) @Ezra-Yu
• Move process_mmdet_results into inference.py (#831) @ly015
• Update resource limit (#783) @jin-s13
• Use COCO 2D pose model in 3D demo examples (#785) @ly015
• Change model zoo titles in the doc from center-aligned to left-aligned (#792, #797) @ly015
• Support MIM (#706, #794) @ly015
• Update out-of-date configs (#827) @jin-s13
• Remove opencv-python-headless dependency by albumentations (#833) @ly015
• Update QQ QR code in README_CN.md (#832) @ly015

MMPose V0.16.0 Release

mmpose.demo.mp4

Highlights

1. Support "ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search" CVPR'2021 (#742,#755).
2. Support MPI-INF-3DHP dataset (#683,#746,#751).
3. Add webcam demo tool (#729)
4. Add 3d body and hand pose estimation demo (#704, #727).

New Features

• Support "ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search" CVPR'2021 (#742,#755)
• Support MPI-INF-3DHP dataset (#683,#746,#751)
• Support Webcam demo (#729)
• Support Interhand 3d demo (#704)
• Support 3d pose video demo (#727)
• Support H36m dataset for 2d pose estimation (#709,#735)
• Add scripts to generate mim metafile (#749)

Bug Fixes

• Fix typos (#692,#696,#697,#698,#712,#718,#728)
• Change model download links from http to https (#716)

Breaking Changes

• Switch to MMCV MODEL_REGISTRY (#669)

Improvements

• Refactor MeshMixDataset (#752)
• Rename 'GaussianHeatMap' to 'GaussianHeatmap' (#745)
• Update out-of-date configs (#734)
• Improve compatibility for breaking changes (#731)
• Enable to control radius and thickness in visualization (#722)
• Add regex dependency (#720)

MMPose V0.15.0 Release

Highlights

1. Support 3d video pose estimation (VideoPose3D).
2. Support 3d hand pose estimation (InterNet).
3. Improve presentation of the model zoo.

New Features

• Support "InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image" (ECCV‘20) (#624)
• Support "3D human pose estimation in video with temporal convolutions and semi-supervised training" (CVPR'19) (#602,#681)
• Support 3d pose estimation demo (#653,#670)
• Support bottom-up whole-body pose estimation (#689)
• Support mmcli (#634)

Bug Fixes

• Fix opencv compatibility (#635)
• Fix demo with UDP (#637)
• Fix bottom-up model onnx convertion (#680)
• Fix GPU_IDS in distributed training (#668)
• Fix MANIFEST.in (#641,#657)
• Fix docs (#643,#684,#688,#690,#692)

Breaking Changes

• Reorganize configs by tasks, algorithms, datasets, and techniques (#647)
• Rename heads and detectors (#667)

Improvements

• Add radius and thickness parameters in visualization (#638)
• Add trans_prob parameter in TopDownRandomTranslation (#650)
• Switch to MMCV MODEL_REGISTRY (#669)
• Update dependencies (#674,#676)

MMPose V0.14.0 Release

Highlights

1. Support animal pose estimation with 7 popular datasets.
2. Support "A simple yet effective baseline for 3d human pose estimation" (ICCV'17).

New Features

• Support "A simple yet effective baseline for 3d human pose estimation" (ICCV'17) (#554,#558,#566,#570,#589)
• Support animal pose estimation (#559,#561,#563,#571,#603,#605)
• Support Horse-10 dataset (#561), MacaquePose dataset (#561), Vinegar Fly dataset (#561), Desert Locust dataset (#561), Grevy's Zebra dataset (#561), ATRW dataset (#571), and Animal-Pose dataset (#603).
• Support bottom-up pose tracking demo (#574).
• Support FP16 training (#584,#616,#626).
• Support NMS for bottom-up (#609).

Bug Fixes

• Fix bugs in the top-down demo, when there are no people in the images (#569).
• Fix the links in the doc (#612).

Improvements

• Speed up top-down inference (#560)
• Update github CI (#562,#564)
• Update Readme (#578,#579,#580,#592,#599,#600,#607)
• Update Faq (#587,#610)

MMPose V0.13.0 Release

Highlights

1. Support Wingloss.
2. Support RHD hand dataset.

New Features

• Support Wingloss (#482)
• Support RHD hand dataset (#523, #551)
• Support Human3.6m dataset for 3d keypoint detection (#518, #527)
• Support TCN model for 3d keypoint detection (#521, #522)
• Support Interhand3D model for 3d hand detection (#536)
• Support Multi-task detector (#480)

Bug Fixes

• Fix PCKh@0.1 calculation (#516)
• Fix unittest (#529)
• Fix circular importing (#542)
• Fix bugs in bottom-up keypoint score (#548)

Improvements

• Update config & checkpoints (#525, #546)
• Fix typos (#514, #519, #532, #537, )
• Speed up post processing (#535)
• Update mmcv version dependency (#544)

MMPose V0.12.0 Release

Highlights

1. Support DeepPose algorithm.

New Features

• Support DeepPose algorithm (#446, #461)
• Support interhand3d dataset (#468)
• Support Albumentation pipeline (#469)
• Support PhotometricDistortion pipeline (#485)
• Set seed option for training (#493)
• Add demos for face keypoint detection (#502)

Bug Fixes

• Change channel order according to configs (#504)
• Fix num_factors in UDP encoding (#495)
• Fix configs (#456)

Breaking Changes

• Refactor configs for wholebody pose estimation (#487, #491)
• Rename decode function for heads (#481)

Improvements

• Update config & checkpoints (#453,#484,#487)
• Add README in Chinese (#462)
• Add tutorials about configs (#465)
• Add demo videos for various tasks (#499, #503)
• Update docs about MMPose installation (#467, #505)
• Rename stat.py to stats.py (#483)
• Fix typos (#463, #464, #477, #481)
• latex to bibtex (#471)
• Update FAQ (#466)

MMPose V0.11.0 Release

Highlights

1. Support fashion landmark detection.
2. Support face keypoint detection.
3. Support pose tracking with MMTracking.

New Features

• Support fashion landmark detection (DeepFashion) (#413)
• Support face keypoint detection (300W, AFLW, COFW, WFLW) (#367)
• Support pose tracking demo with MMTracking (#427)
• Support face demo (#443)
• Support AIC dataset for bottom-up methods (#438, #449)

Bug Fixes

• Fix multi-batch training (#434)
• Fix sigmas in AIC dataset (#441)
• Fix config file (#420)

Breaking Changes

• Refactor Heads (#382)

Improvements

• Update documentation (#409, #412, #415, #416, #419, #421, #422, #424, #425, #435, #436, #437, #444, #445)
• Add GAP (global average pooling) neck (#414)
• Speed up (#411, #423)
• Support COCO test-dev test (#433)