Improved Training of Wasserstein GANs in Pytorch
This is a replication of gan_64x64.py
from Improved Training of Wasserstein GANs but written in Pytorch instead of Tensorflow.
Prerequisites
- Python >= 3.6
- Pytorch Latest version from master branch
- Numpy
- SciPy
- tensorboardX (installation here). It is very convenient to see costs and results during training with TensorboardX for Pytorch
- TensorFlow for tensorboardX
Model
gan_64x64.py
: This model is mainly based onGoodGenerator
andGoodDiscriminator
ofgan_64x64.py
model from Improved Training of Wasserstein GANs. It has been trained on LSUN dataset for around 100k iters.
Result
Some samples after 100k iters of training
Sample 1 | Sample 2 |
---|---|
Testing
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