tag:github.com,2008:https://github.com/tensorlayer/HyperPose/releases 2021-06-30T17:53:11Z tag:github.com,2008:Repository/146084605/v2.2.0 2021-06-30T18:01:40Z <ul> <li>OpenPifPaf model support (Python Training &amp; C++ Inference), 3.1x SPEED UP 🚀🚀🚀</li> <li>Docker container updated to 2.2.0: <a href="https://hub.docker.com/repository/docker/tensorlayer/hyperpose" rel="nofollow">https://hub.docker.com/repository/docker/tensorlayer/hyperpose</a> <ul> <li>support CUDA 10 series (low driver requirement) and advanced CUDA 10.2 - CuDNN 8 - TensorRT 8 series.</li> </ul> </li> <li>Pip installation! <a href="https://pypi.org/project/hyperpose/" rel="nofollow">https://pypi.org/project/hyperpose/</a></li> <li>Add a bunch of new pre-trained models, please check: <a href="https://drive.google.com/drive/folders/1w9EjMkrjxOmMw3Rf6fXXkiv_ge7M99jR" rel="nofollow">https://drive.google.com/drive/folders/1w9EjMkrjxOmMw3Rf6fXXkiv_ge7M99jR</a> <ul> <li>OpenPifPaf, OpenPose-VGGv2, OpenPose-MobileNet</li> </ul> </li> <li>Heavily refactored documentation for a better reading experience! <a href="https://hyperpose.readthedocs.io/en/latest/index.html" rel="nofollow">https://hyperpose.readthedocs.io/en/latest/index.html</a></li> </ul> ganler tag:github.com,2008:Repository/146084605/2.2.0-alpha 2021-06-26T13:45:22Z <ul> <li>OpenPifPaf model support (Python Training + C++ Inference);</li> <li>Docker container updated to 2.2.0: <a href="https://hub.docker.com/repository/docker/tensorlayer/hyperpose" rel="nofollow">https://hub.docker.com/repository/docker/tensorlayer/hyperpose</a></li> <li>Add a bunch of new pre-trained models, please check: <a href="https://drive.google.com/drive/folders/1w9EjMkrjxOmMw3Rf6fXXkiv_ge7M99jR" rel="nofollow">https://drive.google.com/drive/folders/1w9EjMkrjxOmMw3Rf6fXXkiv_ge7M99jR</a></li> <li>Refactored documents.</li> </ul> ganler tag:github.com,2008:Repository/146084605/2.1.0 2020-08-30T08:55:01Z <ul> <li>Docker support: <a href="https://hub.docker.com/repository/docker/tensorlayer/hyperpose" rel="nofollow">https://hub.docker.com/repository/docker/tensorlayer/hyperpose</a></li> <li>HyperPose command-line tool: <code>hyperpose-cli</code></li> <li>Add functionality to keep the original aspect ratio(this is good for precision).</li> <li>New README.</li> <li>Visualization: <ul> <li>Line size varies with person size.</li> <li>Translucent connection line in <code>hyperpose-cli</code>.</li> </ul> </li> </ul> ganler tag:github.com,2008:Repository/146084605/2.0.0 2020-08-17T04:10:09Z <p>Key Features:</p> <ul> <li>Python Training Module <ul> <li>User-defined model arch</li> <li>MS COCO + MPII dataset support</li> <li>User-defined dataset filter and training pipeline</li> </ul> </li> <li>C++ Accelerated Prediction <ul> <li>Operator API</li> <li>Stream API</li> </ul> </li> <li>More model supports <ul> <li>OpenPose</li> <li>Lightweight-OpenPose</li> <li>PoseProposal Network</li> </ul> </li> <li><a href="https://hyperpose.readthedocs.io/en/latest/" rel="nofollow">Documentation</a></li> <li><a href="https://drive.google.com/drive/folders/1w9EjMkrjxOmMw3Rf6fXXkiv_ge7M99jR?usp=sharing" rel="nofollow">More pretrained models</a>(Continuous updating)</li> </ul> ganler tag:github.com,2008:Repository/146084605/1.0.0 2020-05-04T13:30:12Z <p>The 1st version of OpenPose-Plus provides the functionality to do low-level inference, local training, and distributed training. The inference API of the 1st version is quite straightforward and low-level(without much high-level abstraction).</p> <p>As a new version of OpenPose-Plus is upcoming, we made the old version a release.</p> ganler tag:github.com,2008:Repository/146084605/v1.0 2020-04-11T06:34:03Z <p>compatibility fix</p> ganler