suitable parameter for WGAN on mnist?

tdeboissiere / DeepLearningImplementations

Implementation of recent Deep Learning papers

MIT License

1.81k stars 650 forks source link

suitable parameter for WGAN on mnist? #40

Closed jiangzidong closed 7 years ago

jiangzidong commented 7 years ago

Hi, I tried to use the WGAN on mnist, with cmd python main.py --backend=tensorflow --generator deconv --use_mbd

After several epochs, the G_loss and D_loss are both negative value and very close to zero (e.g. -8.7654*e-7) And the generated pictures have mode-missing issue.

Do you have a workable parameter for mnist dataset?

My result: first 2 row are generated image. current_batch

tdeboissiere commented 7 years ago

Not on the top of my head sorry. In theory, the default should work decently well. Try lowering the learning rates to improve results. I generally get better results with upconv architecture instead of deconv.