Implementation of lightweight GAN proposed in ICLR 2021 in Pytorch
lightweight-gan
512×512 flowers after 12 hours of training, 1 gpu
256×256 flowers after 12 hours of training, 1 gpu
Pizza
‘Lightweight’ GAN
Implementation of ‘lightweight’ GAN proposed in ICLR 2021, in Pytorch. The main contributions of the paper is a skip-layer excitation in the generator, paired with autoencoding self-supervised learning in the discriminator. Quoting the one-line summary “converge on single gpu with few hours’ training, on 1024 resolution sub-hundred images”.
Install
$ pip install lightweight-gan
Use
One command
$ lightweight_gan --data ./path/to/images --image-size 512
Model will be saved to ./models/{name} every 1000 iterations, and samples from the model saved to ./results/{name}. name will be default, by default.