Pytorch implementation of conditional generative adversarial network (cGAN) using DCGAN architecture for generating 32x32 images of MNIST, SVHN, FashionMNIST, and USPS datasets.
Run commands (also available in scripts.sh):
| Dataset | Run command |
|---|---|
| MNIST | python main.py --dataset mnist --epochs 25 --n_channels 1 |
| Fashion MNIST | python main.py --dataset fashionmnist --epochs 50 --n_channels 1 |
| SVHN | python main.py --dataset svhn --epochs 100 --n_channels 3 |
| USPS | python main.py --dataset usps --epochs 100 --n_channels 1 |
