TransWikia.com

Preserve colour in convolutional autoencoder

Data Science Asked by Lau on July 3, 2021

at the moment i work with convolutional autoencoder and now I’am looking for paper or methods that adresses a colour preversation. Most of the AE paper use grayscale images and loss functions such as SSIM that preserve the structure very well are also focused on grayscale images. My networks are good in preserving structure (with SSIM as loss) but have a hard time representing the right colour.

I use a all convolution architecture without any pooling. my downsampling is derived by strides > 1 and the upsampling is obtained by transpose convolution.

One Answer

Try training with more epochs. I've seen this same thing where the output after M epochs is a grayscale image but continued training results in more and more color.

Answered by tpetrie on July 3, 2021

Add your own answers!

Ask a Question

Get help from others!

© 2024 TransWikia.com. All rights reserved. Sites we Love: PCI Database, UKBizDB, Menu Kuliner, Sharing RPP