This is the final project for the course 'CSE 351 - Artificial Intelligence' at Habib University. We implemented the paper 'Colorful Image Colorization' and made a demo application on iOS to showcase our results. Due to the unavailability of high-performance systems, we used the algorithm to train our model on only images having flowers from the dataset accessible here.
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.
You will need the following hardware and softwares to run the project.
- A machine running on MacOS.
- An iOS device running iOS 9 or later.
- Apple Developer Account.
- Google Account for development on colab.
Clone the repository and run the server through the following commands after install all the dependencies
python PythonServer/server.py
Now install all CocoaPods dependencies using
cd iOSDemo/
pod install
Now open the iOS Project in XCode and replace your machine's IP in the requestURL variable of the ViewController.swift class. Then install and run the application on your iOS device.
Note: For running the notebook file, download the file and open it in Google Co-Laboratory for features such as mounting gdrive to work.
| Images that worked | Images that didn't work |
|---|---|
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
See the list of contributors who participated in this project.
This project is licensed under the MIT License - see the LICENSE.md file for details
- Dr. Saleha Raza for offering the course and for her support and supervision.
- Olga Belitskaya for the flower image dataset.