https://github.com/kainoj/colnet
🖌️ Automatic Image Colorization with Simultaneous Classification – based on "Let there be Color!"
https://github.com/kainoj/colnet
automatic-colorization cnn colorization convolutional-neural-networks image-colorization machine-learning pytorch
Last synced: 2 days ago
JSON representation
🖌️ Automatic Image Colorization with Simultaneous Classification – based on "Let there be Color!"
- Host: GitHub
- URL: https://github.com/kainoj/colnet
- Owner: kainoj
- Created: 2018-10-28T13:18:07.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2024-07-25T10:13:30.000Z (10 months ago)
- Last Synced: 2024-11-14T08:36:24.325Z (6 months ago)
- Topics: automatic-colorization, cnn, colorization, convolutional-neural-networks, image-colorization, machine-learning, pytorch
- Language: Python
- Homepage:
- Size: 3.78 MB
- Stars: 41
- Watchers: 2
- Forks: 9
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 🖌️ Automatic Image Colorization
Implementation of [_Let there be Color!_](http://iizuka.cs.tsukuba.ac.jp/projects/colorization/en/)
by Satoshi Iizuka, Edgar Simo-Serra and Hiroshi Ishikawa.
_Colorized 100 years old photo of Książ Castle:_
[More images](colorized/colorized.md)
_Other colorized images:_
### First run
[Places365-Standard](http://places2.csail.mit.edu/download.html)
dataset will be downloaded and split into _train/dev/test_ subsets.
By default only 10 arbitrary categories will be considered.
```bash
$ git clone https://github.com/kainoj/colnet.git
$ cd colnet
$ make dataset
$ make split
```
### Requirements
Code is written in Python 3.6.3. [Here](requirements.txt) are all requirements, hit the following to install:
```bash
pip3 install -r requirements.txt
```
### Network training
Simply run:
```bash
$ python3 loader.py config/places10.yaml
```
[`places10.yaml`](./config/places10.yaml) is a sample configuration file – i.e. specifies
total number of epoch, learning rate, output directories etc.
To see full .yaml configuration, `run python3 loader.py config/places10.yaml`
Checkpoints of models are saved on every epoch.
Training can be interrupted and resumed anytime.
Resume by executing:
```bash
$ python3 loader.py config/places10.yaml --model model.pt
```
where `model.pt` is a previously saved model checkpoint.
### Colorize!
Choose the most favourite model and hit:
```bash
$ python3 colorize.py img.jpg ./models/places.pt
```