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
tocust_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
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
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 |
|
- |
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. |
- |
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
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 (#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
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
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
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
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
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
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)
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
Highlights
- 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
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
- Update MSELoss (#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
Highlights
- Support "ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search" CVPR'2021 (#742,#755).
- Support MPI-INF-3DHP dataset (#683,#746,#751).
- Add webcam demo tool (#729)
- 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
tohttps
(#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)
Highlights
- Support 3d video pose estimation (VideoPose3D).
- Support 3d hand pose estimation (InterNet).
- Improve presentation of modelzoo.
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 conversion (#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
andthickness
parameters in visualization (#638) - Add
trans_prob
parameter inTopDownRandomTranslation
(#650) - Switch to
MMCV MODEL_REGISTRY
(#669) - Update dependencies (#674, #676)
Highlights
- Support animal pose estimation with 7 popular datasets.
- 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)
Highlights
- Support Wingloss.
- 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)
Highlights
- 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
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
tostats.py
(#483) - Fix typos (#463, #464, #477, #481)
- latex to bibtex (#471)
- Update FAQ (#466)
Highlights
- Support fashion landmark detection.
- Support face keypoint detection.
- 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
Breaking Changes
- Refactor Heads (#382)
Improvements
- Update readme (#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)
Highlights
- Support more human pose estimation methods.
- Support pose tracking.
- Support multi-batch inference.
- Add some useful tools, including
analyze_logs
,get_flops
,print_config
. - Support more backbone networks.
New Features
- Support UDP (#353, #371, #402)
- Support multi-batch inference (#390)
- Support MHP dataset (#386)
- Support pose tracking demo (#380)
- Support mpii-trb demo (#372)
- Support mobilenet for hand pose estimation (#377)
- Support ResNest backbone (#370)
- Support VGG backbone (#370)
- Add some useful tools, including
analyze_logs
,get_flops
,print_config
(#324)
Bug Fixes
- Fix bugs in pck evaluation (#328)
- Fix model download links in README (#396, #397)
- Fix CrowdPose annotations and update benchmarks (#384)
- Fix modelzoo stat (#354, #360, #362)
- Fix config files for aic datasets (#340)
Breaking Changes
- Rename
image_thr
todet_bbox_thr
for top-down methods.
Improvements
- Organize the readme files (#398, #399, #400)
- Check linting for markdown (#379)
- Add faq.md (#350)
- Remove PyTorch 1.4 in CI (#338)
- Add pypi badge in readme (#329)
Highlights
- Support more human pose estimation methods.
- Support video pose estimation datasets.
- Support Onnx model conversion.
New Features
- Support MSPN (#278)
- Support RSN (#221, #318)
- Support new post-processing method for MSPN & RSN (#288)
- Support sub-JHMDB dataset (#292)
- Support urls for pre-trained models in config files (#232)
- Support Onnx (#305)
Bug Fixes
Breaking Changes
post_process=True|False
andunbiased_decoding=True|False
are deprecated, usepost_process=None|default|unbiased
etc. instead (#288)
Improvements
- Enrich the model zoo (#256, #320)
- Set the default map_location as 'cpu' to reduce gpu memory cost (#227)
- Support return heatmaps and backbone features for bottom-up models (#229)
- Upgrade mmcv maximum & minimum version (#269, #313)
- Automatically add modelzoo statistics to readthedocs (#252)
- Fix Pylint issues (#258, #259, #260, #262, #265, #267, #268, #270, #271, #272, #273, #275, #276, #283, #285, #293, #294, #295)
- Improve README (#226, #257, #264, #280, #296)
- Support PyTorch 1.7 in CI (#274)
- Add docs/tutorials for running demos (#263)
Highlights
- Support more human pose estimation datasets.
- Support more 2D hand keypoint estimation datasets.
- Support adversarial training for 3D human shape recovery.
- Support multi-stage losses.
- Support mpii demo.
New Features
- Support CrowdPose dataset (#195)
- Support PoseTrack18 dataset (#220)
- Support InterHand2.6 dataset (#202)
- Support adversarial training for 3D human shape recovery (#192)
- Support multi-stage losses (#204)
Bug Fixes
- Fix config files (#190)
Improvements
- Add mpii demo (#216)
- Improve README (#181, #183, #208)
- Support return heatmaps and backbone features (#196, #212)
- Support different return formats of mmdetection models (#217)
Highlights
- Support HMR for 3D human shape recovery.
- Support WholeBody human pose estimation.
- Support more 2D hand keypoint estimation datasets.
- Add more popular backbones & enrich the modelzoo
- ShuffleNetv2
- Support hand demo and whole-body demo.
New Features
- Support HMR for 3D human shape recovery (#157, #160, #161, #162)
- Support COCO-WholeBody dataset (#133)
- Support Frei-hand dataset (#125)
- Support CMU Panoptic HandDB dataset (#144)
- Support H36M dataset (#159)
- Support ShuffleNetv2 (#139)
- Support saving best models based on key indicator (#127)
Bug Fixes
Improvements
- Add tools to transform .mat format to .json format (#126)
- Add hand demo (#115)
- Add whole-body demo (#163)
- Reuse mmcv utility function and update version files (#135, #137)
- Enrich the modelzoo (#147, #169)
- Improve docs (#174, #175, #178)
- Improve README (#176)
- Improve version.py (#173)
Highlights
- Add more popular backbones & enrich the modelzoo
- ResNext
- SEResNet
- ResNetV1D
- MobileNetv2
- ShuffleNetv1
- CPM (Convolutional Pose Machine)
- Add more popular datasets:
- Support 2d hand keypoint estimation.
- Support bottom-up inference.
New Features
- Support OneHand10K dataset (#52)
- Support MPII dataset (#55)
- Support MPII-TRB dataset (#19, #47, #48)
- Support OCHuman dataset (#70)
- Support AIChallenger dataset (#87)
- Support multiple backbones (#26)
- Support CPM model (#56)
Bug Fixes
- Fix configs for MPII & MPII-TRB datasets (#93)
- Fix the bug of missing
test_pipeline
in configs (#14) - Fix typos (#27, #28, #50, #53, #63)
Improvements
- Update benchmark (#93)
- Add Dockerfile (#44)
- Improve unittest coverage and minor fix (#18)
- Support CPUs for train/val/demo (#34)
- Support bottom-up demo (#69)
- Add tools to publish model (#62)
- Enrich the modelzoo (#64, #68, #82)
Highlights
- MMPose is released.
Main Features
- Support both top-down and bottom-up pose estimation approaches.
- Achieve higher training efficiency and higher accuracy than other popular codebases (e.g. AlphaPose, HRNet)
- Support various backbone models: ResNet, HRNet, SCNet, Houglass and HigherHRNet.