The mask should be calculated latent space, matching the latent width and height. When you are seeing it visualized they are doing basic upsampling which is why you notice the mask looks blocky/pixelated. Your mask should be a single channel.
The mask should be calculated latent space, matching the latent width and height. When you are seeing it visualized they are doing basic upsampling which is why you notice the mask looks blocky/pixelated. Your mask should be a single channel.