Reputation: 11
Can I create a color image with a GAN consisting of only FC layers?
I understand that in order to create a color image, three channel information of input data must be maintained inside the network. However, data must be flattened to pass through the linear layer. If so, can GAN consisting of only FC layer generate only black and white images?
Upvotes: 1
Views: 86
Answers (1)
Reputation: 40768
Your fully connected network can generate whatever you want. Even three channel outputs. However, the question is: does it make sense to do so? Flattened your input will inherently lose all kinds of spatial and feature consistency that is naturally available when represented as an RGB map.
Remember that an RGB image can be thought of as 3-element features describing each spatial location of a 2D image. In other words, each of the three channels gives additional information about a given pixel, considering these channels as separate entities is a loss of information.
Upvotes: 1
Related Questions
- GAN Model Code Modification — 3 Channels to 1 Channel
- StyleGAN how to generate B image using A source image
- No trained GAN generator using 3 channel produce only grey images
- Using unlabelled custom images instead of Mnist and CIFAR for a simple GAN with Pytorch
- Generate images from a grayscale trained GAN pkl file
- Import transparent images to GAN
- PyTorch: How to convert pretrained FC layers in a CNN to Conv layers
- Is it possible to generate multiple images of the same target using StyleGAN?
- GANs on color images
- How to change a Pytorch CNN to take color images instead of black and white?