Changelog¶
v0.14.0 (06/05/2021)¶
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 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
Support Wingloss.
Support RHD hand dataset.
New Features
Support Wingloss (#482)
Support Human3.6m dataset for 3d keypoint detection (#518, #527)
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
Support DeepPose algorithm.
New Features
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
v0.11.0 (31/01/2021)¶
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)
Bug Fixes
Breaking Changes
Refactor Heads (#382)
Improvements
v0.10.0 (31/12/2020)¶
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 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 CrowdPose annotations and update benchmarks (#384)
Fix config files for aic datasets (#340)
Breaking Changes
Rename
image_thr
todet_bbox_thr
for top-down methods.
Improvements
v0.9.0 (30/11/2020)¶
Highlights
Support more human pose estimation methods.
Support video pose estimation datasets.
Support Onnx model conversion.
New Features
Support MSPN (#278)
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
Set the default map_location as ‘cpu’ to reduce gpu memory cost (#227)
Support return heatmaps and backbone features for bottom-up models (#229)
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)
Support PyTorch 1.7 in CI (#274)
Add docs/tutorials for running demos (#263)
v0.8.0 (31/10/2020)¶
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 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
v0.7.0 (30/9/2020)¶
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 CMU Panoptic HandDB dataset (#144)
Support H36M dataset (#159)
Support ShuffleNetv2 (#139)
Support saving best models based on key indicator (#127)
Bug Fixes
Improvements
v0.6.0 (31/8/2020)¶
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 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)
Improvements
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.