/dcgan-pytorch

PyTorch Implementation of DCGAN

Primary LanguagePythonGNU General Public License v3.0GPL-3.0

dcgan-pytorch

This is an implementaiton of DCGAN, as introduced in the paper "UNSUPERVISED REPRESENTATION LEARNING WITH DEEP CONVOLUTIONAL GENERATIVE ADVERSARIAL NETWORKS" by Alec Radford et al.

Prerequisites

  • python>=3.9.12

  • torch==1.13.1

  • torchvision==0.14.1

You can install required packages by:

pip3 install -r requirements.txt

Training

python3 train.py

Specify TRAIN_IMG_DIR in the script before training.

Contributing

If you find a bug, create a GitHub issue, or even better, submit a pull request. Similarly, if you have questions, simply post them as GitHub issues.