Download Latest Version mmdeploy-1.3.1-linux-x86_64-cxx11abi-cuda11.8.tar.gz (969.0 MB)
Email in envelope

Get an email when there's a new version of MMDeploy

Home / v1.0.0
Name Modified Size InfoDownloads / Week
Parent folder
mmdeploy-1.0.0-linux-x86_64-cxx11abi-cuda11.3.tar.gz 2023-04-06 366.5 MB
0
mmdeploy-1.0.0-linux-x86_64-cxx11abi.tar.gz 2023-04-06 21.9 MB
0
mmdeploy-1.0.0-linux-x86_64-cuda11.3.tar.gz 2023-04-06 366.5 MB
0
mmdeploy-1.0.0-linux-x86_64.tar.gz 2023-04-06 22.0 MB
0
mmdeploy-1.0.0-windows-amd64-cuda11.3.zip 2023-04-06 389.6 MB
0
mmdeploy-1.0.0-windows-amd64.zip 2023-04-06 42.9 MB
0
MMDeploy Release V1.0.0.tar.gz 2023-04-06 5.3 MB
0
MMDeploy Release V1.0.0.zip 2023-04-06 6.3 MB
0
README.md 2023-04-06 4.2 kB
0
Totals: 9 Items   1.2 GB 0

What's Changed

🎉 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.

🚀 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 multi_scale_deform_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)

🔥 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 mmdeploy_python to mmdeploy_runtime (#1821)
  • Update toolset of prebuild image (#1932)
  • Update introduction image (#1937)

🐞 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)

📚 Documentations

  • Update get_started for installation from pypi (#1947)

🌐 Other

  • Bump version to v1.0.0 (#1960)

New Contributors

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

Source: README.md, updated 2023-04-06