TorchGAN
TorchGAN is a Pytorch based framework for designing and developing Generative Adversarial Networks. This framework has been designed to provide building blocks for popular GANs and also to allow customization for cutting edge research. Using TorchGAN's modular structure allows
- Trying out popular GAN models on your dataset.
- Plug in your new Loss Function, new Architecture, etc. with the traditional ones.
- Seamlessly visualize the training with a variety of logging backends.
Installation
Using pip (for stable release):
$ pip3 install torchgan
Using pip (for latest master):
$ pip3 install git+https://github.com/torchgan/torchgan.git
From source:
$ git clone https://github.com/torchgan/torchgan.git
$ cd torchgan
$ python setup.py install
Documentation
The documentation is available here
The documentation for this package can be generated locally.
$ git clone https://github.com/torchgan/torchgan.git
$ cd torchgan/docs
$ pip install -r requirements.txt
$ make html
Now open the corresponding file from build
directory.
Contributing
We appreciate all contributions. If you are planning to contribute bug-fixes, please do so without any further discussion. If you plan to contribute new features, utility functions or extensions, please first open an issue and discuss the feature with us. For more detailed guidelines head over to the official documentation.
Tutorials
The examples
directory contain a set of tutorials to get you started with torchgan. Some of these notebooks are available on Google Colab (they are linked in the tutorials themselves). Additionally, these tutorials can be tried out using the binder link provided.
Authors
This package is currently maintained by
- Avik Pal (@avik-pal)
- Aniket Das (@Aniket1998)
- Yatin Dandi (@yatindandi)