Yining Li

Simple tricks include using lightweight models for detection and pose estimation and removing unnecessary nodes (e.g. unimportant models, visualization, and diagnosis). To further speed up the inference, you may need...

Thanks for your feedback, the download link seems outdated and we will update it asap. You can download the annotations from their website: https://mks0601.github.io/InterHand2.6M/

Most of our demos use 'cuda:0' as the default device for model inference. Could you please specify the demo script and arguments you used when encountering this issue?

Could you please check the GPU availability by the following commands? ```bash python -c "import torch; print(torch.cuda.is_available())" ```

Hi, we will close this issue for now. Please feel free to reopen it if there are further questions.

@xinxinxinxu Thanks for reporting this issue. The modification is indeed necessary for users who would like to implement their own backbone. Would you be willing to submit a pull request...

A basic example can be found in the verification part of the script `tools/deployment/python2onnx.py`: https://github.com/open-mmlab/mmpose/blob/master/tools/deployment/pytorch2onnx.py#L77 You can also refer to [MMDeploy](https://github.com/open-mmlab/mmdeploy) for more information. We recommend using MMDeploy for the...

MMDeploy supports model export with dynamic input size. An example (for a classification model) can be found here: https://github.com/open-mmlab/mmdeploy/blob/master/configs/mmcls/classification_dynamic.py Please note that if a top-down pose model is used, the...

@lamhust2008 If you are using 0.x version of MMPose and MMDeploy, please refer to #1090 for using dynamic shape. For 1.x version, the following docs may be what you need:...

Hi, you can try this tool for inference speed benchmarking: https://github.com/open-mmlab/mmpose/blob/master/tools/analysis/benchmark_inference.py. The demo script is meant to show the usage of inference interfaces and its efficiency may be limited by...