Collection of Generative Adversarial Networks developed using TorchGAN
Generative MultiAdversarial Networks (GMAN)\
Link to Paper\
Requires the torchgan
master.
Training GANs with Binary Neurons by End-to-end Backpropagation\
Link to Paper\
Requires the torchgan
master.
We are open to accepting any model that you have built. The only things to keep in mind are the following:
isort
and yapf
(in this order only) for
formatting the code properly.To run these models you need to have torchgan
installed.
Then simply move into the directory.
$ python3 <model name.py> --help
This will show you the configurable options that are available.
The aim of this repository is to demonstrate the usage of torchgan. We believe this is best done if users can simply download the script and run it without having to download hundreds of GBs of dataset. However, we shall definitely add more models in the future which are specifically designed for high resolution data.