v0.11.6

Bug Fixes

• Fix import Sequence from collections for python compatibility. (#333)

v0.11.5

New Features

• Support export onnx model for yolox. (#330)

Bug Fixes

• Fix timm version compatibility. (#331)

v0.11.4

Bug Fixes

• Fix numpy high version compatibility (#327)

v0.11.3

Bug Fixes

• Fix numpy high version compatibility (#325)

v0.11.2

Bug Fixes

• Fix sklearn requirement (#317)

v0.11.1

Bug Fixes

• Fix modelscope setuptools version conflict (#314)

v0.11.0

New Features

• Support EasyCV as a plug-in for modelscope. (#303)

v0.10.0

Highlights

• Support STDC, STGCN, ReID and Multi-len MOT.
• Support multi processes for predictor data preprocessing. For the model with more time consuming in data preprocessing, the speedup can reach more than 50%.

New Features

• Support multi processes for predictor data preprocessing. (#272)
• Support STDC model. (#284) (#286)
• Support ReID and Multi-len MOT. (#285) (#295)
• Support STGCN model, and support export blade model. (#293) (#299)
• Add pose model zoo and support export torch jit and blade model for pose models. (#294)
• Support train motchallenge and crowdhuman datasets for detection models. (#265)

Improvements

• Speed up inference for face detector when using mtcnn. (#273)
• Add mobilenet config for itag and imagenet dataset, and optimize ClsSourceImageList api to support string label. (#276) (#283)
• Support multi-rows replacement for first order parameter. (#282)
• Add a tool to convert itag dataset to raw dataset. (#290)
• Add PoseTopDownPredictor to replace TorchPoseTopDownPredictorWithDetector (#296)

Bug Fixes

• Remove git lfs dependencies. (#278)
• Fix wholebody keypoints evaluation. (#287)
• Fix DetSourceRaw while label file and image file not match. (#289)

v0.9.0

Highlights

• Support Single-lens MOT (#258)
• Support video recognition (X3D, SWIN-video) (#256)

New Features

• Add inception config and voc config for FCN and UperNet (#261)
• Add inference time under V100 for the benchmark of deitiii and hydra attention (#251)
• Add bev-blancehybrid benchmark (#249)

Improvements

• Optimize data source apis (#254)
• Update predict.py to support input model directory (#252)

Bug Fixes

• Fix MAE arg error after timm upgrade (#255)
• Fix export SSL models bug, avoid loading default pretrained backbone model (#257)
• Fix bug can't find config files while easycv is installed (#253)

v0.8.0

Highlights

• Add BEVFormer and improve the performance of BEVFormer (#224)
• Add DINO++ and support objects365 pretrain (#242)

New Features

• Add DeiT of Hydra Attention version (#220)
• Add EdgeViTv3 (#214)
• Add BEVFormer and improve the performance of BEVFormer (#224)
• Add DINO++ and support objects365 pretrain (#242)

Improvements

• Unify the parsing method of config scripts, and support both local and pai platform products (#235)
• Add more data source apis for open source datasets, involving classification, detection, segmentation and keypoints tasks. And part of the data source apis support automatic download. For more information, please refer to data_hub (#206 #229)
• Add confusion matrix metric for Classification models (#241)
• Add prediction script (#239)

Bug Fixes

• Sync the predict config in the config file for predictor (#238)
• Fix index of image_scale with y2 with bottom_left implemented in _mosaic_combine (#231)
• Add bevformer benchmark and fix classification predict bug (#240)