Fig. 2From: The secure steganography for hiding images via GANThe structure of encoder network The entire work is composed of three blocks: three downsampling layers, nine residual layers, and three upsampling layers. In the downsampling phase, the channels of image gradually increase from 6 to 256. In the residual layers, the channels and size of feature maps are maintained at 256 and 64. In the upsampling layers, the channels of feature maps gradually reduce from 256 to 3Back to article page