Improved Wgan Pytorch Save

Improved WGAN in Pytorch

Project README

Improved Training of Wasserstein GANs in Pytorch

This is a Pytorch implementation of from Improved Training of Wasserstein GANs.

To do:

  • Support parameters in cli *
  • Add requirements.txt *
  • Add Dockerfile if possible
  • Multiple GPUs *
  • Clean up code, remove unused code *

* not ready for conditional gan yet


  • Example:

Fresh training

CUDA_VISIBLE_DEVICES=0,1,2,3 python --train_dir /path/to/train --validation_dir /path/to/validation/ --output_path /path/to/output/ --dim 64 --saving_step 300 --num_workers 8

Continued training:

CUDA_VISIBLE_DEVICES=0,1,2,3 python --train_dir /path/to/train --validation_dir /path/to/validation/ --output_path /path/to/output/ --dim 64 --saving_step 300 --num_workers 8 --restore_mode --start_iter 5000


  • This model is mainly based on GoodGenerator and GoodDiscriminator of model from Improved Training of Wasserstein GANs. It has been trained on LSUN dataset for around 100k iters.
  • ACGAN implementation, trained on 4 classes of LSUN dataset


1. WGAN: trained on bedroom dataset (100k iters)

Sample 1 Sample 2

2. ACGAN: trained on 4 classes (100k iters)

  • dining_room: 1
  • bridge: 2
  • restaurant: 3
  • tower: 4
Sample 1 Sample 2


During the implementation of this model, we built a test module to compare the result between original model (Tensorflow) and our model (Pytorch) for every layer we implemented. It is available at compare-tensorflow-pytorch


Results such as costs, generated images (every 200 iters) for tensorboard will be written to ./runs folder.

To display the results to tensorboard, run: tensorboard --logdir runs


Open Source Agenda is not affiliated with "Improved Wgan Pytorch" Project. README Source: jalola/improved-wgan-pytorch
Open Issues
Last Commit
1 year ago

Open Source Agenda Badge

Open Source Agenda Rating