Mark Hanslip

I've just run into the exact same issue. As a side note, I had to manually downgrade my TensorFlow from v2 to v1 using: import tensorflow.compat.v1 as tf tf.disable_v2_behavior()

Hey Jordan, I've just revisited this codebase and I'm having a similar problem. It was working fine for me middle of last year but now it progresses incredibly slowly -...

Thanks for responding - I'm using TF 1.14 in the env I setup for WaveGAN, maybe I should downgrade to 1.12?

Hi, I believe the correct parameter is `--wavegan_disc_phaseshuffle 0`. I've also experienced the same behaviour as you (still filling up the shuffle buffer when phase shuffle is supposedly turned off)....

Hi, I experienced something similar when training with phaseshuffle - my guess is that with some setups, phaseshuffle uses CPU and so there's a lot of back and forth between...

I have the exact same issue here. Tried defining z, G_z etc as tf.placeholder(tf.int32) before passing to graph.get_tensor_by_name() as per [this](https://github.com/tensorflow/tensorflow/issues/10632) issue but still no joy.

Hi @luisArandas, Did you manage to get this working? It was working fine for me with TF 1.13 middle of last year, but now I'm revisiting it and it no...

Thanks for sorting this out, appreciated. It was getting annoying to have to restart Colab every time it gave me an A100

It seems the files libtorch.dylib, libtorch_cpu.dylib and libc10.dylib are the culprits here, will update if I find a fix

Hey, I'm having a similar issue with FluidBufNMF. I'm running the most recent stable FluCoMa build with SuperCollider 3.10.0 in Ubuntu 20.04. I was just trying to get this example...