MMDeploy Release V0.13.0

What's Changed

🚀 Features

• [Feature] Support feature map output for mmsegmentation by @irexyc in #1625
• [Feature] Pose tracker C/C++/Python API&demos by @lzhangzz in #1663
• [Feature] Add coco whole-body skeleton for pose tracker demo by @lzhangzz in #1736

💥 Improvements

• [Enhancement] Support auto release note by @grimoire in #1589
• [Enhancement] suppress onnx optimizer warning by @grimoire in #1593
• [Enhancement] Better unit test. by @grimoire in #1619
• [Enhancement] update log ext in regression test by @RunningLeon in #1608
• [Enhancement] Speedup TopDownAffine by CropResizePad by @irexyc in #1486
• [Enhancement] Generate supported-backends markdown table by @kaizhong2021 in #1374
• [Enhancement] improvement(tools/scripts): pip install with user environment by @tpoisonooo in #1660
• [Enhancement] remove MMDEPLOY_BUILD_SDK_CXX_API option by @lvhan028 in #1688
• [Enhancement] Optimize C++ demos by @lzhangzz in #1715
• [Enhancement] enable TRT parse ONNX model from file by @AllentDan in #1735
• [Enhancement] Support cmake configure when system exists multiple cuda versions. by @irexyc in #1740
• [Enhancement] Loosen protobuf version criteria for onnx upgrade by @goodsong81 in #1759

🐞 Bug fixes

• [Fix] Fix example standalone build for msvc by @irexyc in #1626
• [Fix] Fix visualize api bug by @hanrui1sensetime in #1641
• [Fix] coreml by @grimoire in #1658
• [Fix] Fix several bugs in the preprocessing of single channel images by @lzhangzz in #1666
• [Fix] fix ascend by @grimoire in #1667
• [Fix]fix trt nms jetson by @grimoire in #1686
• [Fix] fix instance norm double free by @grimoire in #1748
• [Fix] Fix WarpBbox and memory leak in TextRecognizer by @lzhangzz in #1745
• [Fix] Fix build error on windows-cuda platform by @irexyc in #1598
• [Fix] Fix debug build for PoseTracker by @lzhangzz in #1601
• [Fix] Fix aligned allocations on Android by @lzhangzz in #1612
• [Fix] miniconda.sh errors in Dockerfile by @nghiaho12 in #1599
• [Fix] codebase version by @tpoisonooo in #1643
• [Fix] fix rknn output index error in SDK by @AllentDan in #1683
• [Fix] lint by @triple-Mu in #1685
• [Fix] Fixed ncnn model conversion errors in Dockerfile（no module name 'ncnn. ncnn',） by @KerwinKai in #1696
• [Fix] Fix dbnet regression test by @AllentDan in #1704
• [Fix] fix torch allocator resouce releasing by @AllentDan in #1708
• [Fix] fix stale workflow by @RunningLeon in #1713
• [Fix] Add an option to flip webcam inputs for pose tracker demo by @lzhangzz in #1725
• [Fix] Fix bug in remove_imports by @eugene123tw in #1743

📚 Documentations

• [Doc] Fix Android build doc on master branch by @hanrui1sensetime in #1620

🌐 Other

• [Refactor] Support batch inference with shape clustering by @lzhangzz in #1668
• bump version to v0.13.0 by @grimoire in #1753

New Contributors

• @kaizhong2021 made their first contribution in #1374
• @KerwinKai made their first contribution in #1696
• @eugene123tw made their first contribution in #1743
• @goodsong81 made their first contribution in #1759

Full Changelog: v0.12.0...v0.13.0