pixel / README.md
calcuis's picture
Update README.md
a425064 verified
|
raw
history blame
1.07 kB
metadata
license: mit

pixel

A PyTorch-based Generative Adversarial Network (GAN) for training and generating pixel art images.

Setup for model training

Git clone the pixel repo:

git clone https://github.com/mochiyaki/pixel

Get inside the cloned folder:

cd pixel

Train your model

Start training with your dataset (in ./data/):

python trainer.py

screenshot

  • kick start the training process with defined script

screenshot

  • training epoch above; see the example plot below

screenshot

Interact with the post-trained model

When finished, check the model file (in ./models/) then run the inference:

python generator.py

screenshot

  • for technical details, please check it out from this repo