This repository contains code, notebooks, and a summary of a deep learning project with the goal of colorizing black and white movies. The project is described in detail in the project report, and for a detailed description of its implementation, see project notebook.
In short, the project is split into two parts. The first part is a network constructed from scratch and trained on basic examples of fruits to gain understanding of the underlying workflow. The second part builds a more complicated network based on the ResNet-18 architecture and is trained on images from IMDb for the purpose of adding color to classic black and white movies.
