Wwupup
Wwupup
@zaidao2023 你好，我重新clone项目并安装环境后直接执行该语句，无法复现问题。
> [@Wwupup](https://github.com/Wwupup) Hi, > > I noticed that your device is currently connected via USB 2.0, which is likely the cause of the issue. For the Gemini 335, we recommend...
> [@Wwupup](https://github.com/Wwupup) Thank you for your detailed feedback. To help us identify the root cause more quickly, could you please share the firmware version of your Gemini 335 camera, as...
Hello, @LuisGF93 , I’m not sure what caused the problem, it might be that you installed the wrong version of mmcv, please install the version in the README. Also, the...
@Gopal518 Hello, please strictly follow the steps in the readme to create the environment, ensuring that python=3.7, pytorch=1.7, MMCV=1.3.17. I have not tested other environments, so I am not sure...
@tingyulan @Gopal518 Hello follow this should be worked. ``` conda create -n yunet python=3.8 conda install pytorch torchvision torchaudio cudatoolkit=11.1 -c pytorch-lts -c nvidia pip install mmcv-full==1.3.17 -f https://download.openmmlab.com/mmcv/dist/cu111/torch1.8.0/index.html python...
Hello @cubicimage, libfacedetection repo has been updated first to match this version. You can just train model in this mmdet framework and run `python tools/yunet2cpp.py ./configs/yunet_s.py` to get the facedetection-data.cpp.
Hello, @hopeux the current project does not support batch inference.
Hello @leiqinhong, you can find that weight file in old version: https://github.com/ShiqiYu/libfacedetection.train/tree/1688402dbd9b9fc4a3a6793810f558b7407ff384/tasks/task1/weights/yunet_final.pth
你好，我还没有尝试过Web端推理。但是我看了下报错原因应该是tfpn模块的上采样操作的问题。你可以尝试将`nearest`改成`bilinear`或者其他mode再导出为onnx来进行推理。 https://github.com/ShiqiYu/libfacedetection.train/blob/68073e86fdc56014df47deb21cc1a340d66e0bb1/mmdet/models/necks/tfpn.py#L33-L40