stoneyang
@Yuliang-Zou Thanks for your hint! You've saved my day! @Ai-is-light This is perhaps because the cuda code cannot be compiled successfully. In my case, I found error like `nvcc: command...
@spandantiwari Thanks for your hint. I will try upgrading pytorch to the latest version and report further progress.
@spandantiwari I've suceeded exporting pytorch model to onnx weights, without changing my environment, adding normalization op into the onnx weights! Then I converted pytorch from 0.4.0 to 1.0.1 (this is...
> @spandantiwari I've suceeded exporting pytorch model to onnx weights, without changing my environment, adding normalization op into the onnx weights! Then I converted pytorch from 0.4.0 to 1.0.1 (this...
@spandantiwari Oh, I see. I have already started to try other versions, and further info will be updated asap.
P.S.: The very code can be successfully built on Mac book and it runs.
@XinyiXuXD It's a routine tool of original caffe. On Linux, you could find it under `build/tools`.
> Thank you for your reply. > All default parameters are used. I used the batch size of 64 as mentioned in magic-point_shapes.yaml > I tried the number GPUs from...
You need to make directory `crop-images` and subdirectories `face` and `non-face` before running this script. Further, you may wonder how to call some python function like `makedir` to generate the...
@qiuqiangkong thanks for sharing out the data! Are corresponding video clips included in this 1.1TB bundle?