patch_based_cnn
patch_based_cnn copied to clipboard
the implement of Face Anti-Spoofing Using Patch and Depth-Based CNNs
Awesome work on the implementation!! I saw that "depth_fasd.pth" is missing from the output/models folder. It is referenced in the test script: https://github.com/shicaiwei123/patch_based_cnn/blob/master/test/depth_cnn_test.py
请问代码中只有文章中的two streams independently, 没有fusion-based method 测试吗?
为什么depth_cnn_train.py中需要test_loader?毕竟train_pixel_supervise函数中没看到它的使用? 另外该函数中 ``` # no testing the result of mse is also the evluaate factor for depth estimate ``` 这句话怎么理解?
像素级监督疑惑
深度图这一部分网络最后的输入是一副特征图?实际应用时怎么做分类呢?标量监督最后会给出0或1代表预测的物体类别,那么像素级监督最后的输出是特征图要怎么做分类呢?
'lib' directory is not uploaded in the master branch. Can you please update it asap?
I have been following this paper for face anti spoofing and had executed patch based cnn but finding some difficulty in extracting features for depth based CNN. If you have...
Hi, First of all, this repo is a gem. Truly helped me to better understand the paper. Already tried the end to end flow with patch based cnn using casia...