Alias Free Gan Pytorch Save

Unofficial implementation of Alias-Free Generative Adversarial Networks. ( in PyTorch

Project README


Unofficial implementation of Alias-Free Generative Adversarial Networks. ( This implementation contains a lot of my guesses, so I think there are many differences to the official implementations


First create lmdb datasets:

python --out LMDB_PATH --n_worker N_WORKER --size SIZE1,SIZE2,SIZE3,... DATASET_PATH

This will convert images to jpeg and pre-resizes it. This implementation does not use progressive growing, but you can create multiple resolution datasets using size arguments with comma separated lists, for the cases that you want to try another resolutions later.

Then you can train model in distributed settings

python --n_gpu N_GPU --conf config/config-t.jsonnet training.batch=BATCH_SIZE path=LMDB_PATH supports Weights & Biases logging. If you want to use it, add wandb=true arguments to the script.


Latent translation sample 1 Latent translation sample 2 Latent translation sample 3 Latent translation sample 4 Latent translation sample 5 Latent translation sample 6

Open Source Agenda is not affiliated with "Alias Free Gan Pytorch" Project. README Source: rosinality/alias-free-gan-pytorch
Open Issues
Last Commit
8 months ago

Open Source Agenda Badge

Open Source Agenda Rating