Changelog

v0.14.0 (06/05/2021)

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

v0.13.0 (31/03/2021)

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

v0.12.0 (28/02/2021)

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

v0.11.0 (31/01/2021)

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

v0.10.0 (31/12/2020)

Highlights

  1. Support more human pose estimation methods.
  2. Support pose tracking.
  3. Support multi-batch inference.
  4. Add some useful tools, including analyze_logs, get_flops, print_config.
  5. 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 to det_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)

v0.9.0 (30/11/2020)

Highlights

  1. Support more human pose estimation methods.
  2. Support video pose estimation datasets.
  3. 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

  • Fix model download links in README (#255, #315)

Breaking Changes

  • post_process=True|False and unbiased_decoding=True|False are deprecated, use post_process=None|default|unbiased etc. instead (#288)

Improvements

v0.8.0 (31/10/2020)

Highlights

  1. Support more human pose estimation datasets.
  2. Support more 2D hand keypoint estimation datasets.
  3. Support adversarial training for 3D human shape recovery.
  4. Support multi-stage losses.
  5. Support mpii demo.

New Features

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)

v0.7.0 (30/9/2020)

Highlights

  1. Support HMR for 3D human shape recovery.
  2. Support WholeBody human pose estimation.
  3. Support more 2D hand keypoint estimation datasets.
  4. Add more popular backbones & enrich the modelzoo
    • ShuffleNetv2
  5. Support hand demo and whole-body demo.

New Features

Bug Fixes

  • Fix typos in docs (#121)
  • Fix assertion (#142)

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)

v0.6.0 (31/8/2020)

Highlights

  1. Add more popular backbones & enrich the modelzoo
    • ResNext
    • SEResNet
    • ResNetV1D
    • MobileNetv2
    • ShuffleNetv1
    • CPM (Convolutional Pose Machine)
  2. Add more popular datasets:
  3. Support 2d hand keypoint estimation.
  4. Support bottom-up inference.

New Features

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)

v0.5.0 (21/7/2020)

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.