only "queue = False" worked ?

andabi / deep-voice-conversion

Deep neural networks for voice conversion (voice style transfer) in Tensorflow

MIT License

3.92k stars 843 forks source link

only "queue = False" worked ? #29

Closed ThomasXu18 closed 6 years ago

ThomasXu18 commented 6 years ago

When i set "queue = False" to train net1, only take 3h. and the loss is 25%. But when i use "queue = True" , its stuck. GPU is GTX 1080Ti. Thanks for help!

vivek-sethia commented 6 years ago

I have the same issue, for the network 1

ThomasXu18 commented 6 years ago

@vivek-sethia I trained net 1 for 4000 epochs without queue. The loss is 70%. and trianed net2 for 10000+ epochs. The result is not perfect. I am trying to improve it for better results