Mmdeploy

What's Changed
🚀 Features
* [Feature] CodeCamp 101: Support MMDetection 3.x RTMDet model deployment on RV1126 by Qingrenn in https://github.com/open-mmlab/mmdeploy/pull/1551
* [Feature] Support more MMOCR models: DBNet++, TextSnake, ABINet, MRCNN by AllentDan in https://github.com/open-mmlab/mmdeploy/pull/1534
* [Feature] Support RTMDet-Ins. by RangiLyu in https://github.com/open-mmlab/mmdeploy/pull/1662
* [Feature] Add coco whole-body skeleton (1736) by lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1742
💥 Improvements
* [Enhancement] [cherry-pick: 1688] remove MMDEPLOY_BUILD_SDK_CXX_API option by lvhan028 in https://github.com/open-mmlab/mmdeploy/pull/1692
* [Enhancement] Add 320x320 static config for tensorrt by hanrui1sensetime in https://github.com/open-mmlab/mmdeploy/pull/1689
* [Enhancement] Add mmyolo CI on mmdeploy by hanrui1sensetime in https://github.com/open-mmlab/mmdeploy/pull/1650
* [Enhancement] enable TRT parse ONNX model from file by AllentDan in https://github.com/open-mmlab/mmdeploy/pull/1734
* [Enhancement] check in tensorrt-fp16 deployment config for simcc by lvhan028 in https://github.com/open-mmlab/mmdeploy/pull/1741
🐞 Bug fixes
* [Fix] Fix build error on cuda10.2 platform by irexyc in https://github.com/open-mmlab/mmdeploy/pull/1597
* [Fix] fix log info typo of check env by AllentDan in https://github.com/open-mmlab/mmdeploy/pull/1613
* [Fix] Fix typo in LetterResize transform by lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1618
* [Fix] fix no test_step error in TorchWrapper by AllentDan in https://github.com/open-mmlab/mmdeploy/pull/1600
* [Fix] Fixed calling miniconda script in Dockerfile by nghiaho12 in https://github.com/open-mmlab/mmdeploy/pull/1629
* [Fix] fix numba numpy version not compatiable in circileci by RunningLeon in https://github.com/open-mmlab/mmdeploy/pull/1611
* [Fix] Fix the performance test for RKNN by AllentDan in https://github.com/open-mmlab/mmdeploy/pull/1583
* [Fix] Substitute SyncBN with BN for mmpose by hanrui1sensetime in https://github.com/open-mmlab/mmdeploy/pull/1631
* [Fix] fix headless device visualize by grimoire in https://github.com/open-mmlab/mmdeploy/pull/1630
* [Fix] Fix preprocess_model_config for CIFAR dataset by hanrui1sensetime in https://github.com/open-mmlab/mmdeploy/pull/1659
* [Fix] fix rknn output index error in SDK by AllentDan in https://github.com/open-mmlab/mmdeploy/pull/1682
* [Fix] fix lint by triple-Mu in https://github.com/open-mmlab/mmdeploy/pull/1680
* [Fix] fix coreml for branch 1.x by grimoire in https://github.com/open-mmlab/mmdeploy/pull/1669
* [Fix] fix mmpose regression codec sdk export by irexyc in https://github.com/open-mmlab/mmdeploy/pull/1684
* [Fix] fix rknn quantization pipeline by AllentDan in https://github.com/open-mmlab/mmdeploy/pull/1636
* [Fix] fix nms trt jetson 1.x by grimoire in https://github.com/open-mmlab/mmdeploy/pull/1687
* [Fix] import torchvision in wrapper by grimoire in https://github.com/open-mmlab/mmdeploy/pull/1702
* [Fix] fix mmaction2 visualizer by irexyc in https://github.com/open-mmlab/mmdeploy/pull/1703
* [Fix] fix build_backend_model() error by AllentDan in https://github.com/open-mmlab/mmdeploy/pull/1705
* [Fix] fix torch allocator resouce releasing by AllentDan in https://github.com/open-mmlab/mmdeploy/pull/1711
* [Fix] fix mmocr create input from np.ndarray by AllentDan in https://github.com/open-mmlab/mmdeploy/pull/1721
* [Fix] Fix double free 1.x by grimoire in https://github.com/open-mmlab/mmdeploy/pull/1749
* [Fix] Fix `WarpBbox` and memory leak in `TextRecognizer` (1745) by lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1752
* [Fix] remove score filtering in rtmdet_head rewriter since it leads to error shape in batch inference by lvhan028 in https://github.com/open-mmlab/mmdeploy/pull/1762
* [Fix] fix MRCNN visualization, add condition for mask resize by AllentDan in https://github.com/open-mmlab/mmdeploy/pull/1767
📚 Documentations
* [Docs] update build doc for jetsons by AllentDan in https://github.com/open-mmlab/mmdeploy/pull/1621
* [Docs] Correct document errors in `build_from_source.md` master -> 1.x by linjie111 in https://github.com/open-mmlab/mmdeploy/pull/1700
* [Docs] Update docs by Xiangxu-0103 in https://github.com/open-mmlab/mmdeploy/pull/1709
* [Docs] Add twitter discord medium youtube link by vansin in https://github.com/open-mmlab/mmdeploy/pull/1763
🌐 Other
* [Update] Switch pip to mim in Docs and Dockerfile by xin-li-67 in https://github.com/open-mmlab/mmdeploy/pull/1591
* [Refactor] Support batch inference with shape clustering (1668) by lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1733
* Cherry-pick 1439 to fix 'topk' on different devices for onnxruntime-gpu inference by hanrui1sensetime in https://github.com/open-mmlab/mmdeploy/pull/1603
* cherry-pick 1608 by RunningLeon in https://github.com/open-mmlab/mmdeploy/pull/1637
* Cherry-pick PR 1460 to dev-1.x by hanrui1sensetime in https://github.com/open-mmlab/mmdeploy/pull/1617
* Cherry-pick PR 1366, 1370, 1460, 1577, 1598, 1601, 1612, 1626 to dev-1.x by irexyc in https://github.com/open-mmlab/mmdeploy/pull/1635
* Cherry pick PR 1663, 1666, 1486 to dev-1.x by lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1691
* Cherry pick PR 1625, 1715, 1725 to dev-1.x by lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1726
* Cherry pick PR 1740 to dev-1.x by irexyc in https://github.com/open-mmlab/mmdeploy/pull/1760
* bump version to 1.0.0rc2 by grimoire in https://github.com/open-mmlab/mmdeploy/pull/1754

New Contributors
* linjie111 made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1700
* Xiangxu-0103 made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1709

**Full Changelog**: https://github.com/open-mmlab/mmdeploy/compare/v1.0.0rc1...v1.0.0rc2

Features

- Add profiler for SDK (1446)
- Support MMRotate 1.x (1401)
- Add YOLOv5 support for RV1126 device. (1321)
- Support Torch JIT Modulated Deformable Conv (1536)
- Support SOLO deployment with OpenVINO (1454)
- Support TVM (1531)
- Support Rotated RTMDet deployment (1553)

Improvements

- Refactor SDK registry (1368)
- Avoid copying dense arrays in Python API (1349)
- Update dockerfile pip source (1484)
- Add rknn device check (1363)
- cherry-pick: Decouple preprocess operation and transformation (1353)
- sync 1493 to support TorchAllocator as TensorRT Gpu Allocator and fix DCNv2 tensorrt plugin error (1519)
- Add md link check github action (1320)
- Remove cudnn dependency for transform 'mmaction2::format_shape' (1509)
- Refactor rewriter context for MMRazor (1483)
- Add is_batched argument to pipeline.json (1528)
- Refactor Backend Manager(1515)

Bug fixes

- Support ONNXRuntime-1.13 (1407)
- Fix `det->pose` demo (1419)
- Fix MMOCR import typing error (1497)
- Fix requirements of MMEditing (1496)
- recovery mmdet layers (1526)
- Fix squeeze export and unsqueeze pass for opset 13 (1538)
- Fix 'cannot seek vector iterator' in debug windows build (1543)
- Fix API build error in readthedocs (1567)
- Fix unittest and suppress warning (1552)
- Rename 'forward_test' to 'predict' (1561)
- Fix onnx2ncnn.cpp bugs (1518)

Document

- Add mmaction2 & coreml index for readthedocs (1542)

Contributors

lzhangzz lvhan028 PeterH0323 AllentDan irexyc RunningLeon grimoire hanrui1sensetime pppppM antoszy DDGRCF kota-iizuka liuyanyi

We are excited to announce the release of MMDeploy 1.0.0rc0. MMDeploy 1.0.0rc0 is the first version of MMDeploy 1.x, a part of the OpenMMLab 2.0 projects. Up to the release, MMDeploy 1.x supports OpenMMLab 2.0 based projects: MMCls 1.x, MMDet 3.x, MMDet3d 1.x, MMSeg 1.x, MMEdit 1.x, MMOCR 1.x, MMPose 1.x, MMAction2 1.x.

Features

- Support mmaction2 (1012)
- Support SimCC from mmpose (1187)
- Support RTMDet from MMDet (1104)
- Support CenterNet from MMDet (1219)
- Support MobileOne from MMCls (1268)
- Support external usage of MMYOLO (1088)

Improvements

- Update dockerfiles (1296)

Bug fixes

- Fix test ops (1352)
- Fix: checkpoint load on cpu (1324)

Document

- Add MMYOLO desc in README (1235)
- Modify the links & fix some typos (1150)

Contributors

xin-li-67 liu-mengyang doufengqi PeterH0323 triple-Mu MambaWong isLinXu francis0407 sanbuphy vansin SsTtOoNnEe RangiLyu lvhan028 grimoire AllentDan RunningLeon lzhangzz tpoisonooo hanrui1sensetime

What's Changed
🎉 Highlights

- We are excited to announce the release of MMDeploy v1.0.0 and v0.14.0. MMDeploy v1.0.0 is the first officially released version of MMDeploy 1.x, a part of the OpenMMLab 2.0 projects.
- We switch the default branch to `main` from `master`. MMDeploy 0.x (`master` branch) will be deprecated and new features will only be added to MMDeploy 1.x (`main` branch) in future.
- We provide newly prebuilt mmdeploy packages and users can install mmdeploy through pip and download libraries from github release pages for sdk inference.

🚀 Features

- Support TensorRT engine for onnxruntime (1739)
- Sync csharp apis with newly added c apis && demo (1718)
- Dynamically load net module to remove dependencies of mmdeploy.so (1776)
- Support asf module in FPNC neck from mmocr (1828)
- Sync Java apis with newly added c apis and demo (1856)
- Add support for converting a inpainting model to ONNX and TensorRT (1831)

🔥 Improvements

- Add Model::ReadConfig and simplify handle creation (1738)
- Disable building demos when preparing prebuilt package (1810)
- Add optional softmax in LinearClsHead (1858)
- Add highlight version for mmdeploy 1.x (1871)
- Optimize mmpose postprocess (1887)
- Rename mmdeploy_python to mmdeploy_runtime (1911)
- Update pplnn to v0.9.2 to resolve ci error (1934)
- Upgrade openvino to 2022.3.0 (1944)

🐞 Bug fixes

- Fix palette generation on opencv-3.x (1778)
- Fix trtlogger instead of mm logger (1755)
- Fix normalization to_rgb option (1771)
- Fix missing include for gcc-10 build (1802)
- Avoid linking static libs in monolithic build (1797)
- Fix Debian aarch64 cross compiling (1806)
- Add unified device guard (1855)
- Export mmdeploy only in monolithic build (1798)
- Fix stale workflow (1825)
- Fix pose_tracker python api will raise ValueError when result has no human (1923)
- Fix CascadeRoIHead export when reg_class_agnostic=True in box_head (1900)

📚 Documentations

- Fix typo in docs/en/07-developer-guide/regression_test.md (1907)
- Update get_started for installation from pypi (1950)


🌐 Other
- Bump version to v0.14.0 (1943)

New Contributors
* yhna940 made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1739
* kumailf made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1907
* KKIEEK made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1831

**Full Changelog**: https://github.com/open-mmlab/mmdeploy/compare/v0.13.0...v0.14.0

<!-- Release notes generated using configuration in .github/release.yml at v0.13.0 -->

What's Changed
🚀 Features
* [Feature] Support feature map output for mmsegmentation by irexyc in https://github.com/open-mmlab/mmdeploy/pull/1625
* [Feature] Pose tracker C/C++/Python API&demos by lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1663
* [Feature] Add coco whole-body skeleton for pose tracker demo by lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1736
💥 Improvements
* [Enhancement] Support auto release note by grimoire in https://github.com/open-mmlab/mmdeploy/pull/1589
* [Enhancement] suppress onnx optimizer warning by grimoire in https://github.com/open-mmlab/mmdeploy/pull/1593
* [Enhancement] Better unit test. by grimoire in https://github.com/open-mmlab/mmdeploy/pull/1619
* [Enhancement] update log ext in regression test by RunningLeon in https://github.com/open-mmlab/mmdeploy/pull/1608
* [Enhancement] Speedup TopDownAffine by CropResizePad by irexyc in https://github.com/open-mmlab/mmdeploy/pull/1486
* [Enhancement] Generate supported-backends markdown table by kaizhong2021 in https://github.com/open-mmlab/mmdeploy/pull/1374
* [Enhancement] improvement(tools/scripts): pip install with user environment by tpoisonooo in https://github.com/open-mmlab/mmdeploy/pull/1660
* [Enhancement] remove MMDEPLOY_BUILD_SDK_CXX_API option by lvhan028 in https://github.com/open-mmlab/mmdeploy/pull/1688
* [Enhancement] Optimize C++ demos by lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1715
* [Enhancement] enable TRT parse ONNX model from file by AllentDan in https://github.com/open-mmlab/mmdeploy/pull/1735
* [Enhancement] Support cmake configure when system exists multiple cuda versions. by irexyc in https://github.com/open-mmlab/mmdeploy/pull/1740
* [Enhancement] Loosen protobuf version criteria for onnx upgrade by goodsong81 in https://github.com/open-mmlab/mmdeploy/pull/1759
🐞 Bug fixes
* [Fix] Fix example standalone build for msvc by irexyc in https://github.com/open-mmlab/mmdeploy/pull/1626
* [Fix] Fix visualize api bug by hanrui1sensetime in https://github.com/open-mmlab/mmdeploy/pull/1641
* [Fix] coreml by grimoire in https://github.com/open-mmlab/mmdeploy/pull/1658
* [Fix] Fix several bugs in the preprocessing of single channel images by lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1666
* [Fix] fix ascend by grimoire in https://github.com/open-mmlab/mmdeploy/pull/1667
* [Fix]fix trt nms jetson by grimoire in https://github.com/open-mmlab/mmdeploy/pull/1686
* [Fix] fix instance norm double free by grimoire in https://github.com/open-mmlab/mmdeploy/pull/1748
* [Fix] Fix `WarpBbox` and memory leak in `TextRecognizer` by lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1745
* [Fix] Fix build error on windows-cuda platform by irexyc in https://github.com/open-mmlab/mmdeploy/pull/1598
* [Fix] Fix debug build for PoseTracker by lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1601
* [Fix] Fix aligned allocations on Android by lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1612
* [Fix] miniconda.sh errors in Dockerfile by nghiaho12 in https://github.com/open-mmlab/mmdeploy/pull/1599
* [Fix] codebase version by tpoisonooo in https://github.com/open-mmlab/mmdeploy/pull/1643
* [Fix] fix rknn output index error in SDK by AllentDan in https://github.com/open-mmlab/mmdeploy/pull/1683
* [Fix] lint by triple-Mu in https://github.com/open-mmlab/mmdeploy/pull/1685
* [Fix] Fixed ncnn model conversion errors in Dockerfile（no module name 'ncnn. ncnn',） by KerwinKai in https://github.com/open-mmlab/mmdeploy/pull/1696
* [Fix] Fix dbnet regression test by AllentDan in https://github.com/open-mmlab/mmdeploy/pull/1704
* [Fix] fix torch allocator resouce releasing by AllentDan in https://github.com/open-mmlab/mmdeploy/pull/1708
* [Fix] fix stale workflow by RunningLeon in https://github.com/open-mmlab/mmdeploy/pull/1713
* [Fix] Add an option to flip webcam inputs for pose tracker demo by lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1725
* [Fix] Fix bug in remove_imports by eugene123tw in https://github.com/open-mmlab/mmdeploy/pull/1743
📚 Documentations
* [Doc] Fix Android build doc on master branch by hanrui1sensetime in https://github.com/open-mmlab/mmdeploy/pull/1620
🌐 Other
* [Refactor] Support batch inference with shape clustering by lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1668
* bump version to v0.13.0 by grimoire in https://github.com/open-mmlab/mmdeploy/pull/1753

New Contributors
* kaizhong2021 made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1374
* KerwinKai made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1696
* eugene123tw made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1743
* goodsong81 made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1759

**Full Changelog**: https://github.com/open-mmlab/mmdeploy/compare/v0.12.0...v0.13.0

Features

- Support Torch JIT Modulated Deformable Conv (1508)
- Support TorchAllocator as TesnorRT GPU memory allocator (1493)
- Support TVM backend (1216)
- Support probability output for segmentation (1379)

Improvements

- Add pip source in dockerfile (1492)
- Reformat multi-line logs and strings (1489)
- Refactor backend manager (1475, 1522, 1540)
- Add stale workflow to check issue and PR (1504, 1510)
- Update ppl.nn v0.9.1 and ppl.cv v0.7.1 (1356)
- Add is_batched argument to pipeline.json (1560)
- Build monolithic SDK by default (1577)

Bug fixes

- Fix conversion and inference support for torch 1.13 (1488)
- Remove cudnn dependency for transform 'mmaction2::format_shape' (1509)
- Add build-arch option to build script (1530)
- Fix 'mmaction2::transpose.cu' build failed on cuda-10.2 (1539)
- Fix 'cannot seek vector iterator' in debug windows build (1555)
- Fix ops unittest seg-fault error (1556)

Document

- Add mmaction2 sphinx-doc link (1541)
- Update FAQ about copying onnxruntime dll to 'mmdeploy/lib' (1554)
- Update support_new_backend.md (1574)

Contributors

PeterH0323 grimoire RunningLeon irexyc ouonline tpoisonooo antoszy BuxianChen AllentDan lzhangzz hanrui1sensetime