Code accompanying the paper "Wasserstein GAN"
Two main empirical claims:
python main.py --dataset lsun --dataroot [lsun-train-folder] --cuda
python main.py --mlp_G --ngf 512
Generated samples will be in the
If you plot the value
-Loss_D, then you can reproduce the curves from the paper. The curves from the paper (as mentioned in the paper) have a median filter applied to them:
med_filtered_loss = scipy.signal.medfilt(-Loss_D, dtype='float64'), 101)
More improved README in the works.