This is about an experimental Artificial Intelligent approach for a solution to implement a feed-forward pass in a CNN (" Convolutional Neural Network") where 1.3 million photos of objects and scenes from ImageNet were decomposed using Lab model and used as an input feature ("L") and classification labels ("a" and "b").
This is based on a research work developed at the University of California, Berkeley by Richard Zhang, Phillip Isola, and Alexei A. Efros. Colorful Image Colorization.( link: https://arxiv.org/pdf/1603.08511.pdf )
Applying a Deep Learning algorithm (Feed-Forward CNN), final models were generated and are available here: Zhang et al - Colorful Image Colorization - models Directory with sourcecode of the approaches
Directory contains:
- models - directory that contains all models used to color images and videos
- image_colorization - directory containing scripts for testing the model - coloring the photos
- utils - directory that contains other utils we use in the process