Conditional-PixelCNN-decoder
Conditional-PixelCNN-decoder copied to clipboard
Tensorflow implementation of Gated Conditional Pixel Convolutional Neural Network
https://github.com/anantzoid/Conditional-PixelCNN-decoder/blob/9a5c9a3df2c58100cf5e3600392e67db8ac7a59e/models.py#L30-L34 This has the connection from the vstack to the hstack occuring after the gate, but in Figure 2 of the paper, it occurs after the masked convolution but before...
How exactly does the binarize function work in the code? How do I extend it to the CIFAR model? How does comparing images with random numbers work?
the middle point of mask convolution kernel is zero or one ? The paper show it is zeros. Right?