search

chrisdonahue / wavegan

WaveGAN: Learn to synthesize raw audio with generative adversarial networks
MIT License
1.33k stars 281 forks source link

Sample of D_loss and G_loss Tensorflow Graphs #56

Closed saraalemadi closed 5 years ago

saraalemadi commented 5 years ago

Hi @chrisdonahue,

Can you kindly share the D_loss and G_loss Tensorflow graphs at the end of your WaveGAN training of your experiment which you have mentioned in your paper given that I would like to verify my experiment outcomes against yours.

Thanks in advance

chrisdonahue commented 5 years ago

Sure. These are typical results for a successful run:

https://i.imgur.com/mKMvFaJ.png

chrisdonahue commented 5 years ago

It can vary a bit by dataset though. The first one is for birds, this one is drum soudn effects: https://i.imgur.com/Bexalaj.png

saraalemadi commented 5 years ago

Thanks a lot @chrisdonahue. Do you happen to have the output graphs for the Piano experiment as well? They will be very beneficial for me since the dataset I am working has closer characteristics to it.

chrisdonahue commented 5 years ago

Here is piano: https://i.imgur.com/zj1RNPe.png