Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of mmdeploy

mmdeploy - MMDeploy Release V1.3.1

What's Changed

๐Ÿš€ Features

๐Ÿ’ฅ Improvements

๐Ÿž Bug fixes

๐Ÿ“š Documentations

๐ŸŒ Other

New Contributors

Full Changelog: https://github.com/open-mmlab/mmdeploy/compare/v1.3.0...v1.3.1

- Python
Published by RunningLeon over 2 years ago

mmdeploy - MMDeploy Release V1.3.0

What's Changed

๐Ÿš€ Features

๐Ÿ’ฅ Improvements

๐Ÿž Bug fixes

๐Ÿ“š Documentations

๐ŸŒ Other

New Contributors

Full Changelog: https://github.com/open-mmlab/mmdeploy/compare/v1.2.0...v1.3.0

- Python
Published by RunningLeon over 2 years ago

mmdeploy - MMDeploy Release V1.2.0

What's Changed

๐Ÿš€ Features

๐Ÿ’ฅ Improvements

๐Ÿž Bug fixes

๐Ÿ“š Documentations

๐ŸŒ Other

New Contributors

Full Changelog: https://github.com/open-mmlab/mmdeploy/compare/v1.1.0...v1.2.0

- Python
Published by RunningLeon almost 3 years ago

mmdeploy - MMDeploy Release V1.1.0

What's Changed

๐Ÿš€ Features

๐Ÿ’ฅ Improvements

๐Ÿž Bug fixes

๐Ÿ“š Documentations

๐ŸŒ Other

New Contributors

Full Changelog: https://github.com/open-mmlab/mmdeploy/compare/v1.0.0...v1.1.0

- Python
Published by RunningLeon about 3 years ago

mmdeploy - MMDeploy Release V1.0.0

What's Changed

๐ŸŽ‰ Highlights

  • We are excited to announce the release of MMDeploy v1.0.0. MMDeploy v1.0.0 is the first officially released 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., MMRotate 1.x, MMYOLO.
  • 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 page for sdk inference.

๐Ÿš€ Features

  • Support Vacc Backend (#1679)
  • Dynamically load net module to remove dependencies of mmdeploy.so (#1776)
  • Sync Java apis with newly added c apis and demo (#1795)
  • Add optional softmax in LinearClsHead (#1863)
  • Support mmrazor (#1701)
  • Support multiscaledeform_attn trt plugin (#1844)
  • Sync csharp apis with newly added c apis && demo (#1889)
  • Support RTMDet and RTMPose ncnn deployment (#1857)
  • Support ConformerHead from mmclassification (#1905)

๐Ÿ”ฅ Improvements

  • Upgrade onnx to 1.13.0 to resolve security issue (#1793)
  • Rewrite torch.cat for TensorRT when input is dynamic (#1851)
  • Add github workflow based on self hosted runner (#1751)
  • Optimize mmpose postprocess (#1888)
  • Add rtmpose coreml support (#1902)
  • Add github prebuild workflow after new release (#1852)
  • Rename mmdeploypython to mmdeployruntime (#1821)
  • Update toolset of prebuild image (#1932)
  • Update introduction image (#1937)

๐Ÿž Bug fixes

  • Fix reduction fp16 exceed on android (#1819)
  • Fix unit test in test_codebase (#1790)
  • Fix clip on tensorrt 8.0 (#1833)
  • Fix MobileOne deployment. (#1870)
  • Fix the warning method that calls the trt logger (#1850)
  • Fix rtmdet-ins head (#1884)
  • Fix ascend faster-rcnn (#1842)
  • Fix RTMDet-Ins inference result without mask in SDK (#1867)
  • Fix pose_tracker python api will raise ValueError when result has no human (#1922)
  • Fix mmrotate and regression script (#1917)
  • Add unified device guard (#1855)
  • Fix Debian aarch64 cross compiling (#1806)
  • Export mmdeploy only in monolithic build (#1798)
  • Fix errors about deploying MMYOLO-OpenVINO, DETR, ConvFormer and RTMDet (#1919)

๐Ÿ“š Documentations

  • Update get_started for installation from pypi (#1947)

๐ŸŒ Other

  • Bump version to v1.0.0 (#1960)

New Contributors

  • @doufengqi made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1165
  • @RangiLyu made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1104
  • @MambaWong made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1324
  • @vansin made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1334
  • @sanbuphy made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1398
  • @DDGRCF made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1454
  • @kota-iizuka made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1561
  • @liuyanyi made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1553
  • @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
  • @i-square made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1785
  • @AndyLiu93 made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1679
  • @LKJacky made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1701
  • @cxiang26 made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1844
  • @Joyphy made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1850
  • @FishBigOcean made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1902

Full Changelog: https://github.com/open-mmlab/mmdeploy/compare/v1.0.0rc3...v1.0.0

- Python
Published by RunningLeon about 3 years ago

mmdeploy - MMDeploy Release V0.14.0

What's Changed

๐ŸŽ‰ 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.

๐Ÿš€ 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)

๐Ÿ”ฅ 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 mmdeploypython to mmdeployruntime (#1911)
  • Update pplnn to v0.9.2 to resolve ci error (#1934)
  • Upgrade openvino to 2022.3.0 (#1944)

๐Ÿž 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 regclassagnostic=True in box_head (#1900)

๐Ÿ“š Documentations

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

๐ŸŒ 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

- Python
Published by RunningLeon about 3 years ago

mmdeploy - MMDeploy Release V1.0.0rc3

What's Changed

  • [Fix] Fix palette generation on opencv-3.x by @lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1779
  • [Fix] fix ut and textdet createinput by @AllentDan in https://github.com/open-mmlab/mmdeploy/pull/1756
  • [Fix] turn -DMMDEPLOYSHAREDLIBS=ON when building rknn by @AllentDan in https://github.com/open-mmlab/mmdeploy/pull/1786
  • [FIX] sdk normalization to_rgb option not working(dev1.x) by @SineYuan in https://github.com/open-mmlab/mmdeploy/pull/1792
  • [Enhancement] add Model::ReadConfig & simplify handle creation (#1738) by @lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1794
  • [Fix] Fix tensorrt int8 by @grimoire in https://github.com/open-mmlab/mmdeploy/pull/1799
  • [Fix] Fix component not found issue by changing class YOLOV5Head to class YOLOv5Head by @i-square in https://github.com/open-mmlab/mmdeploy/pull/1785
  • [Fix] Fix package_tools by @irexyc in https://github.com/open-mmlab/mmdeploy/pull/1772
  • [Fix] Avoid linking static libs in monolithic build by @lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1801
  • [Fix] Fix missing include for gcc-10 build (#1802) by @lzhangzz in https://github.com/open-mmlab/mmdeploy/pull/1804
  • [Fix] fix centernet by @grimoire in https://github.com/open-mmlab/mmdeploy/pull/1768
  • [Fix] disable building demos when preparing prebuilt package by @lvhan028 in https://github.com/open-mmlab/mmdeploy/pull/1803
  • bump version to 1.0.0rc3 by @lvhan028 in https://github.com/open-mmlab/mmdeploy/pull/1811

New Contributors

  • @i-square made their first contribution in https://github.com/open-mmlab/mmdeploy/pull/1785

Full Changelog: https://github.com/open-mmlab/mmdeploy/compare/v1.0.0rc2...v1.0.0rc3

- Python
Published by lvhan028 over 3 years ago

mmdeploy - MMDeploy Release V1.0.0rc2

What's Changed

๐Ÿš€ 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 ### ๐Ÿ’ฅ Improvements
  • [Enhancement] [cherry-pick: #1688] remove MMDEPLOYBUILDSDKCXXAPI 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 ### ๐Ÿž 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 preprocessmodelconfig 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 buildbackendmodel() 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 ### ๐Ÿ“š 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 ### ๐ŸŒ 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

- Python
Published by grimoire over 3 years ago

mmdeploy - MMDeploy Release V0.13.0

What's Changed

๐Ÿš€ 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 ### ๐Ÿ’ฅ 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 MMDEPLOYBUILDSDKCXXAPI 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 ### ๐Ÿž 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๏ผˆno module name 'ncnn. ncnn',๏ผ‰ 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 ### ๐Ÿ“š Documentations
  • [Doc] Fix Android build doc on master branch by @hanrui1sensetime in https://github.com/open-mmlab/mmdeploy/pull/1620 ### ๐ŸŒ 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

- Python
Published by grimoire over 3 years ago

mmdeploy - MMDeploy Release V1.0.0rc1

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

- Python
Published by lvhan028 over 3 years ago

mmdeploy - MMDeploy Release V0.12.0

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 supportnewbackend.md (#1574)

Contributors

@PeterH0323 @grimoire @RunningLeon @irexyc @ouonline @tpoisonooo @antoszy @BuxianChen @AllentDan @lzhangzz @hanrui1sensetime

- Python
Published by lvhan028 over 3 years ago

mmdeploy - MMDeploy Release V1.0.0rc0

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

- Python
Published by RunningLeon over 3 years ago

mmdeploy - MMDeploy Release V0.11.0

Features

  • Support MMaction2 TSN and SlowFast deployment with ONNXRuntime and TensorRT (#1183,#1410,#1455)
  • Support Rockchip device RV1126
    • Rewrite BaseDenseHead.get_bboxes to support SSD, FSAF and RetinaNet (#1203)
    • Add BaseDenseHead postprocessing in SDK (#1238)
    • Support YOLOv3 and YOLOv5 postprocessing in SDK (#1280๏ผŒ#1424)
  • Add SDK profiler (#1274)
  • Support end2end deployment for pointpillars & centerpoint(pillar)from MMDet3d (#1178)

Improvements

  • Support loading TensorRT libnvinfer plugins (#1275)
  • Avoid copying dense arrays in SDK C API and Python API (#1261, #1349)
  • Add Core ML common configuration (#1308)
  • Refactor SDK registry (#1368)
  • Update regresssion test to serialize eval result into json (#1310)
  • Support onnxruntime-1.13 API(#1407)
  • Decouple preprocess operation and transformation (#1353)

Bug fixes

  • Set stream argument when using async memcpy (#1314)
  • Use OpenCV with videoio enabled for aarch64 platform (#1343)
  • Fix(tools/scripts): find env file failed (#1385)
  • Fix ncnn-int8 config path (#1380)
  • Fix out-of-boundary issue in SDK when topk is larger than class_num (#1420)
  • Fix yolohead trt8.2 (#1433)
  • Fix pad_to_square (#1436)
  • Fix det_pose demo (#1419)
  • Relax module adapter template constraints (#1366)
  • Fix ncnn torch 1.12 master (#1430)
  • Avoid gpu topk const-fold (#1439)
  • Support .NET Framwork 4.8 and fix batch inference error(#1370)
  • Upgrade ncnn to 20221128 to resolve build error (#1459)

Document

  • Add more images for demos and user guides (#1339)
  • Improve mmdet3d doc (#1394)
  • Display CI results in README (#1452)
  • Fix dead links in write_config.md (#1396)

Contributors

@xin-li-67 @sunjiahao1999 @francis0407 @Typiqally @triple-Mu @lvhan028 @grimoire @AllentDan @RunningLeon @lzhangzz @tpoisonooo @hanrui1sensetime

- Python
Published by RunningLeon over 3 years ago

mmdeploy - MMDeploy Release V0.10.0

Features

  • Support Monocular 3D Detection and FCOS3D Deployment (#1047)
  • Support MMEdit EDSR deployment with ncnn-int8 (#1111)
  • Rewrite Conv2dAdaptiveOps to support EfficientNet deployment (#1045)
  • Add installation scripts for Jetson Orin (#1105)
  • Support aarch64 cross compiler (#1126)

Improvements

  • Support Fast-SCNN deployment with ncnn backend (#1094)
  • Ease rewriter import (#1166)
  • Support TensorRT 8.4 (#1144)
  • Remove extra domains after model extraction (#1207)
  • Add batch inference demos (#986)
  • update symbolic rewriter for latest PyTorch API (#1122)
  • Detect filesystem library in CMake (#1190)
  • compute per sample statistics when profiling in batch mode (#1158)
  • Add a device field for mmdeploy_mat_t (#1176)

Before v0.10.0 C typedef struct mmdeploy_mat_t { uint8_t* data; int height; int width; int channel; mmdeploy_pixel_format_t format; mmdeploy_data_type_t type; } mmdeploy_mat_t; in v0.10.0 C typedef struct mmdeploy_mat_t { uint8_t* data; int height; int width; int channel; mmdeploy_pixel_format_t format; mmdeploy_data_type_t type; mmdeploy_device_t device; } mmdeploy_mat_t;

Bug fixes

  • Fix test_windows_onnxruntime workflow error in circleci (#1254)
  • Fix build error when the target device is 'cuda' and the inference backend is 'onnxruntime-gpu' (#1253)
  • Fix layer_norm symbol error when exporting it with torch>=1.12 (#1168)
  • Fix regression test script errors (#1217, #1146)

Document

  • Update supported backend logos in the cover of README (#1252)
  • Add a link to MMYOLO in README (#1235)

Contributors

@doufengqi @Qingrenn @liu-mengyang @SsTtOoNnEe @OldDreamInWind @sunjiahao1999 @LiuYi-Up @isLinXu @lansfair @lvhan028 @grimoire @AllentDan @RunningLeon @lzhangzz @tpoisonooo @hanrui1sensetime

- Python
Published by lvhan028 over 3 years ago

mmdeploy - MMDeploy Release V0.9.0

Features

  • Add Rust API for mmdeploy SDK. Project: https://github.com/liu-mengyang/rust-mmdeploy
  • Support MMOCR TextSnake and MMPose Hourglass model deployment with ncnn-int8 (#1074, #1064, #1066)
  • Rewrite torch.Tensor.__mod__ to support TensorRT (#1024)

Improvements

  • Separate C++ API demos from C API demos (#1099)
  • Refactor SDK pipeline (#938)
  • Check upstream libopencv-dev version before adding apt repository (#1068)
  • Make inference still available on headless device (#1041)
  • Validate installation in building scripts (#1036)

Bug fixes

  • Set size_divisor of Pad transform to 1 for static shape model. (#1049)
  • Fix LayerNorm shape issue when exporting to onnx with torch <= 1.12 (#1015)
  • Fix calibration error when converting model to TensorRT-int8 (#1050)
  • Synchronize cuda stream after inference with onnxruntime-gpu (#1053)
  • Add GatherTopk TensorRT plugin as a workaround to fix dynamic shape issue (#1033)
  • Fix RoiAlignFunction error for CoreML (#1029)
  • Resolve two-stage detector deployment error with CoreML (#1044)
  • Fix two-stage detector TensorRT deployment error with dynamic shape (#1046)

Document

  • Update supported backends table in README (#1109)
  • Correct examples in tutorial - how to develop TensorRT plugin (#1021)
  • Fix broken links and typos (#1078, #1025, #1061)

Contributors

@liu-mengyang @BrokenArrow1404 @jinwonkim93 @Qingrenn @JingweiZhang12 @ichitaka @Typiqally @lvhan028 @irexyc @tpoisonooo @lzhangzz @grimoire @AllentDan @hanrui1sensetime

- Python
Published by lvhan028 over 3 years ago

mmdeploy - MMDeploy Release V0.8.0

Highlight

  • Support more platforms and devices: RISC-V, Apple M1, Huawei Ascend310 and Rockchip RK3588

Features

  • Support more models on ONNX Runtime and TensorRT
    • mmdetection DETR (#924)
    • mmclassification Swin Transformer (#911)
    • mmdetection3d pointpillars (nus version) (#319)
  • Support more platforms and devices:
    • RISC-V via ncnn (#910)
    • Apple M1 (#760)
    • Huawei Ascend310 (#747)
    • Rockchip RK3588 (#865)
  • Add TorchScript SDK inference backend (#890)
  • Experimental support for fusing transformations in preprocess pipeline by CVFusion (#741)

Improvements

  • Support multi-label classification in SDK (#950)
  • Add the following scripts to simplify mmdeploy installation for some scenarios: (#919)

script | OS version -- | -- buildubuntux64ncnn.py | 18.04/20.04 buildubuntux64ort.py | 18.04/20.04 buildubuntux64pplnn.py | 18.04/20.04 buildubuntux64torchscript.py | 18.04/20.04

  • Add scaled dot-product attention operator for TensorRT (#949)
  • Support model batch inference profiling (#868) shell # profile the latency of resnet18-tensorrt model with batch size 4 python tools/profiler.py \ configs/mmcls/classification_tensorrt_dynamic-224x224-224x224.py \ ../mmclassification/configs/resnet/resnet18_8xb32_in1k.py \ {/the/path/of/an/image/directory} \ --model {work-dirs}/mmcls/resnet/trt/end2end.engine \ --device cuda \ --shape 224x224 \ --num-iter 100 \ --warmup 10 \ --batch-size 4

Bug fixes

  • Fix CI errors (#985, #983, #977, #987, #966, #945)
  • Fix missing sqrt in PAAHead (#984)
  • Fix nms_rotated logic when no bbox is detected (#976)
  • Fix rewrite for torch.Tensor.__setitem__ in some corner cases (#964, #941)
  • Disable ONNX optimizer when converting model to ncnn (#961)
  • Fix regression test (#958)
  • Disable cublaslt for CUDA 10.2 (#947)
  • Stop sorting dataset by default & set test_mode for mmdet pipelines (#920)
  • Resolve the issue (#909) - ValueError: cpu is invalid for the backend tensorrt. when exporting SDK meta info (#912)
  • Validate the device id when the inference backend is TensorRT or OpenVINO (#886)
  • Fix mmdeploypplnnnet build error when target device is CPU (#896)
  • Replace adaptive_avg_pool2d with avg_pool2d to support exporting ONNX with dynamic shape (#857)

Document

  • Clarify arguments in model conversion (#956, #940)
  • Add tutorial in Chinese about "How to write a customized TensorRT plugin" (#290)
  • Keep cmake build option in a separate document cmake_option. (#832)
  • Add project architecture (#882)
  • Sync Enginsh and Chinese documents (#842)
  • Correct build-demo commands in prebuiltpackagewindows.md (#879)
  • Fix the wrong argument in model quantization document (#866)

Known issues

  • DETR deployment failed both via ONNX Runtime and TensorRT (#1011, pytorch 84563) ## Contributors @OldDreamInWind @liu-mengyang @gy-7 @Groexhy @munhou @miraclezqc @VVsssssk @hanrui1sensetime @tpoisonooo @grimoire @irexyc @RunningLeon @AllentDan @lzhangzz @lvhan028

- Python
Published by lvhan028 over 3 years ago

mmdeploy - MMDeploy Release V0.7.0

Highlight

  • Support SNPE (#789)
  • Add C++ API for SDK (#831)

Features

  • Support SNPE (#789)
  • Add C++ API for SDK (#831)
  • Support MMRotate model with le135 angle format (#788)
  • Support RoI Transformer and Gliding Vertex model deployment from MMRotate (#713, #650)
  • Add inference latency test script tools/profile.py (#655) Here is an example to profile TensorRT_fp32-resnet18 inference latency: shell python tools/profile.py \ configs/mmcls/classification_tensorrt_dynamic-224x224-224x224.py \ ../mmclassification/configs/resnet/resnet18_8xb32_in1k.py \ ../mmdetection/demo --model work-dirs/mmcls/resnet/trt/end2end.engine \ --device cuda \ --shape 224x224 \ --num-iter 100 \ --warmup 10

Improvements

  • Optimize prebuilt process for Python SDK (#810)
  • Upgrade ppl.nn and ppl.cv to v0.8.1 and v0.7.0 respectively (#793, #564)
  • Support batch image test in test script test.py (#829)
  • Install onnx optimizer by setuptools instead of cmake build (#690, #811, #843)
  • Add SDK code coverage (#808)
  • Support kwargs in SDK Python bindings (#794, #844, #852)
  • Support building SDK into a single library by enabling MMDEPLOY_BUILD_SDK_MONOLITHIC (#806)
  • Add a new option MMDEPLOY_BUILD_EXAMPLES to build and install SDK examples (#822)
  • Reduce log verbosity and improve error reporting (#755)
  • Upgrade GPU Dockerfile to use TensorRT 8.2.4.2 (#706)
  • Optimize ONNX graph
    • Add a function rewriter to torch.Tensor.__setitem__, eliminating almost 80% nodes for x[:,:,:H,:W] = y onnx export (#704)
    • Add CommonSubgraphElimination onnx pass (#647)
  • [BC Breaking] Standardize C API(#634)
    • Prefix all struct with mmdeploy_ and move all header files into mmdeploy folder. image
  • Rename onnx2ncnn to mmdeploy_onnx2ncnn (#694)

Bug fixes

  • Fix build error on macOS platform (#762)
  • Fix troch.triu function rewriter error when exporting to onnx (#792)
  • Resolve Cascade R-CNN, YOLOX and SATRN deployment failure (#787, #758, #753)
  • Fix check_env.py about checking whether custom ops are available (#785)
  • Fix export for TopK operator in PyTorch 1.12 (#715) Fix export for padding operators in PyTorch<1.10 (#754)
  • Add default topk in SDK model meta info when it is not explicitly specified in mmclassifcation model configs (#702)
  • Fix SingleRoIExtractor for TorchScript backend (#724)
  • Fix export for DistancePointBBoxCoder.decode (#687)
  • Fix wrong backend type when doing calibration (#719)
  • Set exit code to 1 when error happens (#715)
  • Fix build error on android platform (#698)
  • Pass img_metas while exporting to onnx (#681, #700, #707)

Document

  • Update build document for android platform (#817)
  • Fix rendering issues of get_started documents in readthedocs (#740)
  • Add prebuilt package usage on Windows platform (#816)
  • Simplify get_started guide (#813)

Contributors

@nijkah @dwSun @lvhan028 @lzhangzz @irexyc @RunningLeon @grimoire @tpoisonooo @AllentDan @hanrui1sensetime

- Python
Published by lvhan028 almost 4 years ago

mmdeploy - MMDeploy Release V0.6.0

Highlight

  • Support Swin Transformer deployment with TensorRT and ONNX Runtime (#652)
  • Support Segmenter deployment with all backends (#587)
  • Add Java API for SDK (#563)

Features

  • Support Swin Transformer deployment with TensorRT and ONNX Runtime (#652)
  • Add Java API for SDK (#563)
  • Support Segmenter deployment with all backends (#587)
  • Support two-stage rotated detector deployment with TensorRT (#530)

Improvements

  • Add onnx pass to fuse select-assign graph pattern (#589)
  • Add more CircleCI workflows on Linux, Windows and Linux-GPU platforms (#368)
  • Add documentation and sample code for model partitioning (#599)
  • Add GridPriorsTRT plugin to speed up TensorRT anchor generation from 155us t0 13us (#646)
  • Add MMDEPLOY_TASKS variable in cmake scripts to remove duplication code (#606)
  • Improve ncnn patch embed (#592)
  • Support compute capability 87 for Jetson Orin (#601)
  • Adjust csrc structure (#594)

Bug fixes

  • Add build to TensorRT plugin candidate path list (#672)
  • Fix missing "image shape" when exporting mmpose models (#667)
  • Fix ncnn unittest error (#626)
  • Fix bugs when deploying ShuffleNetV2 with TensorRT (#645)
  • Relax mmcls version constraint (#653)
  • Eliminate illegal memory access for object detector C# API (#613)
  • Add dim param for Tensor::Squeeze (#603)
  • Fix link missed issue in index.rst (#607)
  • Add support for MMOCR 0.5+ (#604)
  • Fix output tensor shape of ncnn backend (#605)

Documentation

  • Fix errors and typos in user documents (#676, #675, #655, #654, #621, #588, #586)
  • Update deployment benchmark for ViT (#624)
  • Replace markdown lint with mdformat and configure myst-parser (#610)

Contributors

@zambranohally @bgsuello @triple-Mu @DrRyanHuang @liuqc11 @Yosshi999 @zytx121 @RunningLeon @AllentDan @lzhangzz @irexyc @grimoire @lvhan028 @hanrui1sensetime @tpoisonooo

- Python
Published by lvhan028 almost 4 years ago

mmdeploy - MMDeploy Release V0.5.0

Highlight

  • Provide prebuilt packages since v0.5.0
  • Decouple pytorch2onnx and onnx2backends
  • Support text detection models PANet, PSENet and DBNet, with CUDA accelerated postprocessing in SDK
  • Support MMRotate

Features

  • Add prebuild tools (#545, #347)
  • Experimental executor support in SDK (#497)
  • Support ViT on ncnn (#477, #403)
  • Support LiteHRNet on ncnn (#316)
  • Support more text detection models PANet, PSENet and DBNet, with CUDA accelerated postprocessing in SDK (#446, #526, #534)
  • Add C# API for SDK (#388, #535)
  • Support ncnn quantization (#476)
  • Support RepPoints on TensorRT (#457)
  • Support MMRotate on ONNX Runtime and TensorRT (#277, #312, #422, #450, #428, #473)
  • Support MMRazor (#220, #467)

Improvements

  • Remove spdlog manual installation but still keep it as an option (#423, #544) Users can turn on the following option to use the external spdlog shell cmake .. -DMMDEPLOY_SPDLOG_EXTERNAL=ON
  • Add SDK python demos (#554)
  • Add ONNX passes support (#390)
  • Decouple pytorch2onnx and onnx2backends (#529, #540)
  • Add scripts and configs to test metrics of deployed model with all inference backend (#425, #302, #551, #542)
  • Support MDCN and DeformConv TensorRT FP16 (#503, #468)
  • Add interactive build script for Linux and NVIDIA platform (#399)
  • Optimize global average pooling when exporting ONNX (#478)
  • Refactor onnx2ncnn, add test cases and simplify code (#436)
  • Remove expand operation from mmdet rewrite (#371)

Bug fixes

  • Update CMake scripts to fix building problems (#544, #553)
  • Make ONNXRuntime wrapper work both for cpu and cuda execution (#438, #532)
  • Fix PSPNet-TorchScript conversion error (#538)
  • Resolve the incompatible issue when upgrading MMPose from v0.25.0 to v0.26.0 (#518, #527)
  • Fix mismatched device issue when testing Mask R-CNN deployed model (#511)
  • Remove redundant resize in mmseg EncoderDecoder rewrite (#480)
  • Fix display bugs on headless devices (#451)
  • Fix MMDet3D pillarencode deployment failure (#331)
  • Make the latest spdlog compatible (#423)
  • Fix CI (#462, #447, #440, #426, #441)
  • Fix a bug that causes exporting to onnx failed with static shape and batch size > 1 (#501)
  • Make --work-dir default to$pwd in tools/deploy.py (#483)

Documentation

  • Fix user document errors, reorganize them, update REAME and rewrite the GET_STARTED chapters (#418, #482, #509, #531, #547, #543)
  • Rewrite the get_started for Jetson platforms (#484, #449, #415, #381)
  • Fix APIs rendering failure in readthedocs (#443)
  • Remove '\' in API docstring (#495)
  • More tutorials in Chinese are checked in - Tutorial 05: ONNX Model Editing and Tutorial 04: onnx custom op (#508, #517)

Contributors

@sanjaypavo @PeterH0323 @tehkillerbee @zytx121 @triple-Mu @zhiqwang @gyf304 @lakshanthad @Dchaoqun @zhouzaida @NagatoYuki0943 @VVsssssk @irexyc @RunningLeon @hanrui1sensetime @lzhangzz @grimoire @tpoisonooo @AllentDan @SingleZombie

- Python
Published by lvhan028 almost 4 years ago

mmdeploy - MMDeploy Release V0.4.1

Improvements

  • Add IPython notebook tutorial (#234)
  • Support detecting TensorRT from CUDA_TOOLKIT_ROOT_DIR (#357)
  • Build onnxruntime backend in GPU dockerfile (#366)
  • Add CircleCI workflow for linting (#348)
  • Support saving results when testing the deployed model of MMEdit (#336)
  • Support GPU postprocessing for instance segmentation (#276)

Bug fixes

  • Make empty bounding box list allowed in text recognizer and pose detector C API (#310, #396)
  • Fix the logic of extracting model name from config (#394)
  • Fix feature test for std::source_location (#416)
  • Add missing codegen for sm_53 to support Jetson Nano (#407)
  • Fix crash caused by accessing the wrong tensor in segmentor C API (#363)
  • Fix reading mat type from the wrong image in a batch (#362)
  • Fix missing binary flag when saving temp OpenVINO model (#353)
  • Fix Windows build for pose demo (#307)

Documents

  • Refine documents by fixing typos, correcting build commands, and removing redundant doc tree (#352, #360, #378, #398)
  • Add a tutorial about torch2onnx in Chinese (#365)

Contributors

@irexyc @VVsssssk @AllentDan @lzhangzz @PeterH0323 @RunningLeon @zly19540609 @triple-Mu @grimoire @hanrui1sensetime @SingleZombie @Adenialzz @tpoisonooo @lvhan028 @xizi

- Python
Published by lvhan028 about 4 years ago

mmdeploy - MMDeploy Release V0.4.0

Features

  • Support MMPose model inference in SDK: HRNet, LiteHRNet and MSPN
  • Support MMDetection3D: PointPillars and CenterPoint(pillar)
  • Support Andoid platform so as to benefit the development of android apps
  • Support fcn_unet deployment with dynamic shape
  • Support TorchScript

Improvements

  • Optimize TRTMultiLevelRoiAlign plugin
  • Remove RoiAlign plugin for ONNXRuntime
  • Add DCN TensorRT plugin
  • Update pad logic in detection heads
  • Refactor the rewriter module of Model Converter
  • Suppress CMAKECUDAARCHITECTURES warnings
  • Update cmake scripts to ensure that the thirdparty packages are relocatable

Bug fixes

  • Fix the crash on the headless installation
  • Correct the deployment configs for MMSegmentation
  • Optimize prepocess module and fix the potential use-after-free issue
  • Resolve the compatibility with torch 1.11
  • Fix the errors when deploying yolox model
  • Fix the errors occurred during docker build

Documents

  • Reorganize the build documents. Add more details about how to build MMDeploy on Linx, Windows and Android platforms
  • Publish two chapters about the knowledge of model deployment
  • Update the supported model list, including MMSegmentation๏ผŒMMPose and MMDetection3D
  • Translate the tutorial of "How to support new backends" into Chinese
  • Update the FAQ

Contributors

@irexyc @lvhan028 @RunningLeon @hanrui1sensetime @AllentDan @grimoire @lzhangzz @SemyonBevzuk @VVsssssk @SingleZombie @raykindle @yydc-0 @haofanwang @LJoson @PeterH0323

- Python
Published by lvhan028 about 4 years ago

mmdeploy - MMDeploy Release V0.3.0

Features

  • Support for windows platform.(#106)
  • Support mmpose codebase.(#94)
  • Support GFL model from mmdetection.(#124)
  • Support export hardsigmoid in torch<=1.8.(#169)

Improvements

  • Support mmocr v0.4+.(#115)
  • Upgrade isort in pre-commit config.(#141)
  • Opimize delta2bboxes.(#152)

Bug fixes

  • Fix onnxruntime wrapper for gpu inference. (#123)
  • Fix ci.(#144)
  • Fix tests for OpenVINO with python 3.6. (#125)
  • Added TensorRT version check. (#133)
  • Fix a type error when computing scale_factor in rewriting interpolate.(#185)

Documents

  • Add Chinese documents How_to_support_new_model.md and How_to_write_config.md (#147,#137)

Contributors

A total of 19 developers contributed to this release.

@grimoire @RunningLeon @AllentDan @lvhan028 @hhaAndroid @SingleZombie @lzhangzz @hanrui1sensetime @Vvsssssk @SemyonBevzuk @ypwhs @TheSeriousProgrammer @matrixgame2018 @tehkillerbee @uniyushu @haofanwang @ypwhs @zhouzaida @q3394101

- Python
Published by lvhan028 over 4 years ago

mmdeploy - MMDeploy Release V0.2.0

Features

  • Support Nvidia Jetson deployment. (Nano, TX2, Xavier)
  • Add Python interface for SDK inference. (#27)
  • Support yolox on ncnn. (#29)
  • Support segmentation model UNet. (#77)
  • Add docker files. (#67)

Improvements

  • Add coverage report, CI to GitHub repository. (#16, #34, #35)
  • Refactor the config utilities. (#12, #36)
  • Remove redundant copy operation when converting model. (#61)
  • Simplify single batch NMS. (#99)

Documents

  • Now our English and Chinese documents are available on readthedocs: English ็ฎ€ไฝ“ไธญๆ–‡
  • Benchmark and tutorial for Nvidia Jetson Nano. (#71)
  • Fix docstring, links in documents. (#18, #32, #60, #84)
  • More documents for TensorRT and OpenVINO. (#96, #102)

Bug fixes

  • Avoid outputting empty tensor in NMS for ONNX Runtime. (#42)
  • Fix TensorRT 7 SSD. (#49)
  • Fix mmseg dynamic shape. (#57)
  • Fix bugs about pplnn. (#40, #74)

Contributors

A total of 14 developers contributed to this release.

@grimoire @RunningLeon @AllentDan @SemyonBevzuk @lvhan028 @hhaAndroid @Stephenfang51 @SingleZombie @lzhangzz @hanrui1sensetime @VVsssssk @zhiqwang @tehkillerbee @Echo-minn

- Python
Published by SingleZombie over 4 years ago

mmdeploy - MMDeploy Release V0.1.0

Major Features

  • Fully support OpenMMLab models

We provide a unified model deployment toolbox for the codebases in OpenMMLab. The supported codebases are listed as below, and more will be added in the future - [x] MMClassification (== 0.19.0) - [x] MMDetection (== 2.19.0) - [x] MMSegmentation (== 0.19.0) - [x] MMEditing (== 0.11.0) - [x] MMOCR (== 0.3.0)

  • Multiple inference backends are available

Models can be exported and run in different backends. The following ones are supported, and more will be taken into consideration - [x] ONNX Runtime (>= 1.8.0) - [x] TensorRT (>= 7.2) - [x] PPLNN (== 0.3.0) - [x] ncnn (== 20211208) - [x] OpenVINO (2021 4 LTS)

  • Efficient and highly scalable SDK Framework by C/C++

    All kinds of modules in SDK can be extensible, such as Transform for image processing, Net for Neural Network inference, Module for postprocessing and so on.

Contributors

A total of 11 developers contributed to this release.

@grimoire @lvhan028 @AllentDan @VVsssssk @SemyonBevzuk @lzhangzz @RunningLeon @SingleZombie @del-zhenwu @zhouzaida @hanrui1sensetime

- Python
Published by grimoire over 4 years ago