search

chrisdonahue / wavegan

WaveGAN: Learn to synthesize raw audio with generative adversarial networks
MIT License
1.32k stars 283 forks source link

Bug in infer() #66

Open wenting-zhao opened 4 years ago

wenting-zhao commented 4 years ago

https://github.com/chrisdonahue/wavegan/blob/b2e930a3ad1e36a27642188827f548a9d1db2e3f/train_wavegan.py#L235

This line should be z = graph.get_tensor_by_name('z:0'), otherwise we'll get

ValueError: Cannot feed value of shape (10, 100) for Tensor 'G_z:0', which has shape '(?, 16384, 1)'

Thanks!