An implementation of "CAN: Creative Adversarial Networks"
The aim of this repo is to implement the CAN model that can handle high-resolution images.
Download wikiart data. wikiart dataset available here. Using the dataset is subject to wikiart's terms of use
mkdir data
cd data
mv DOWNLOADED_DATA_PATH ./
unzip wikiart.zip
Install packages required to execute the code.
$ pip install -r requirements.txt
You can train the model with the command below.
$ python main.py
You can test the model with the command below. The trained models are saved in the "checkpoints" directory.
$ python main.py --test --load-from TRAINED_MODEL_PATH