原因：pytorch转换的onnx有很多冗余需要简化

Shape not supported yet!
Gather not supported yet!
  # axis=0
Unsupported unsqueeze axes !
Unknown data type 0
Shape not supported yet!
Gather not supported yet!
  # axis=0
Unsupported unsqueeze axes !
Unknown data type 0
Shape not supported yet!
Gather not supported yet!

pytorch转onnx再转ncnn出错

pytorch生成onnx转换模型时有一些冗余，我们用工具简化一下onnx模型
执行下面命令
pip install onnx-simplifier
python -m onnxsim face.onnx face_sim.onnx 转换就是正常的了
附上大佬的github链接：https://github.com/biubug6/Face-Detector-1MB-with-landmark/issues/1

Windows下ncnn环境配置

https://blog.csdn.net/qq_36890370/article/details/104966786