Conditional Generation of MNIST images using conditional DC-GAN in PyTorch.
Based on the following papers:
- Conditional Generative Adversarial Nets
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Implementation inspired by the PyTorch examples implementation of DCGAN.
Example of sampling results shown below. Each row is conditioned on a different digit label:
python conditional_dcgan.py --cuda --save_dir=models --samples_dir=samples --epochs=25
Feel free to reach to me at malzantot [at] ucla [dot] edu
for any questions or comments.