Unsupervised representation learning with CapsNet based Generative Adversarial Networks
Coalesces Wassertein Distance algorithm based generative adversarial networks with deep convolutinal network based discriminator replaced by CapsNet architecture.
- Python > 3.6
- PyTorch
- TorchVision
- TorchNet
- TQDM
- Visdom [optional]
** For training, an NVIDIA TITAN XP GPU was used. Using CUDA with GPU is strongly recommended. CPU is supported but speed of training will be very slow.
- MNIST
- CIFAR-10
Utilizes FAIR's visdom as visulization tool. If you'd like to visualize the test and train results, run with visualize
args.
$ sudo python3 -m visdom.server &
$ python3 main.py --visualize --cuda
Else, simply run:
$ python3 main.py --dataset cifar10 --dataroot ./data --cuda --niter [NUM_EPOCHS] --
To run with MLP as G or D, run:
$ python3 main.py --dataset cifar10 --dataroot ./data --cuda --experiment {Name} --mlp_G --ngf 512
Please send an email to raeidsaqur[at]cs[dot]toronto[dot]edu for questions, PRs etc.
*** Note: Improved ReadMe is in the works!