-
Having these implementations of baselines and their training curves is a fantastic help -- thanks! Is there any intention of releasing an implementation of DQN-CTS or DQN-PixelCNN at any point?
ezliu updated
6 years ago
-
Thanks for this clear notebook example, I have one question regarding construction of the quantized image:
In the paper, it was mentioned that we could use 'prior' like PixelCNN to model the constr…
-
hi,
I do not know why the WAV should be rescaled during the preprocessing procedure, in this way:
```
if hparams.rescale:
wav = wav / np.abs(wav).max() * hparams.rescaling_max
```
Could you t…
ghost updated
6 years ago
-
Hi,
I really like what you have developed, i think it will be very useful for models like DenseNet.
I tried it on a Keras model I have been working on, i just copied the "monkey patch" from the …
-
There is an error in the implementation of the masks on the horizontal and vertical stacks:
If I use the code to recreate the results from [here](https://github.com/kkleidal/GatedPixelCNNPyTorch/bl…
-
- [ ] (Archy) _I found the maths in [the bilinear transformation] section a bit confusing, probably because I'm not very good at maths, but also because of the number of different nomenclatures flying…
-
Hi,
Thanks for the amazing work! I am wondering why you set out_channels to 30 for the case that is not mu-law quantized. Could you give a little more details about "num_mixture * 3 (pi, mean, log…
-
link: https://deepmind.com/blog/high-fidelity-speech-synthesis-wavenet/
paper: https://deepmind.com/documents/131/Distilling_WaveNet.pdf
referenced from:
- https://twitter.com/heiga_zen/status/…
-
I want to commend the team on their fantastic work. This addition to the PixelCNN++ makes it much more usable for integrators like myself.
I've been attempting to use your package to produce condit…
-
Hi Ryuichi,
Thanks for your great work.
Forgive me if I got this wrong but I think it's not necessary to sum up `log_probs` at the last dimension [here](https://github.com/r9y9/wavenet_vocoder/…