Peng
Peng
We do not provide API for face back. If you want to save a face image, you can directly save the image in the video stream or use the face...
You may need to rotate it 90 degrees and resize it.Better landscape effect.
The file list we provided is suitable for Linux system. According to your error message, it's a path format error.
没有呢，官方还没有放出来。
测试的代码是我写的这个吗，还是其他的平台上进行测试。如果是我写的那个应该是不会这种情况。 你没有说具体的问题，不是很好回答。
没有视频数据，都是图片哈。
If you are only predicting a single image, you only need to take the first two categories of the category.
> Okay, but do what with them, give only two of them to softmax? Are they like preds[0]=fake, and preds[1]=real? > > Also, do I need to detect face in...
https://github.com/SoftwareGift/FeatherNets_Face-Anti-spoofing-Attack-Detection-Challenge-CVPR2019/issues/72#issuecomment-548178960