Skip to main content
Data Science

Return to Question

bold, backtick escapes
Source Link
edit approved Aug 17, 2019 at 23:15
Fatemeh Asgarinejad
edit approved Aug 17, 2019 at 23:15
Fatemeh Asgarinejad
  • 1.2k
  • 1
  • 10
  • 18

I would like to make a neural network which uses black and white images as input and outputs a colored version of it. The important thing in that process is that the size of the images must stay the same. 

Usually this is done by using a Fully Convolutional Network with GANGAN or AE architectureAE architecture. Now I have decided to implement a VAEVAE version, but when i looked it up on the internet I found versions where the latent space was Linear/DenseLinear/Dense meaning it breaks the Full Convolution. 

Is a VAEVAE not a valid Approach for this type of neural network? Or is there a solution/some code someone can provide which would help in that situation? (PytorchPytorch prefered)

I would like to make a neural network which uses black and white images as input and outputs a colored version of it. The important thing in that process is that the size of the images must stay the same. Usually this is done by using a Fully Convolutional Network with GAN or AE architecture. Now I have decided to implement a VAE version, but when i looked it up on the internet I found versions where the latent space was Linear/Dense meaning it breaks the Full Convolution. Is a VAE not a valid Approach for this type of neural network? Or is there a solution/some code someone can provide which would help in that situation? (Pytorch prefered)

I would like to make a neural network which uses black and white images as input and outputs a colored version of it. The important thing in that process is that the size of the images must stay the same. 

Usually this is done by using a Fully Convolutional Network with GAN or AE architecture. Now I have decided to implement a VAE version, but when i looked it up on the internet I found versions where the latent space was Linear/Dense meaning it breaks the Full Convolution. 

Is a VAE not a valid Approach for this type of neural network? Or is there a solution/some code someone can provide which would help in that situation? (Pytorch prefered)

Source Link
Stefan
Stefan
  • 111
  • 3

Fully Convolutional Variational Autoencoder

I would like to make a neural network which uses black and white images as input and outputs a colored version of it. The important thing in that process is that the size of the images must stay the same. Usually this is done by using a Fully Convolutional Network with GAN or AE architecture. Now I have decided to implement a VAE version, but when i looked it up on the internet I found versions where the latent space was Linear/Dense meaning it breaks the Full Convolution. Is a VAE not a valid Approach for this type of neural network? Or is there a solution/some code someone can provide which would help in that situation? (Pytorch prefered)