-
```
# python -m crank.bin.extract_statistics --n_jobs 2 --phase train --conf conf/mlfb_vqvae.yml --scpdir data/scp --featdir data/feature
# Started at Mon Dec 7 14:55:35 UTC 2020
#
INFO:root:# o…
-
## 🐛 Bug
Given a decently large input data size, PyTorch Lightning will crash on v3-128 (and presumably any larger TPU pods too). The same code works fine on a v3-32. If I make the input image size…
-
I am using google colab to run this but since today I can't run it.
I think that this is an issue on their side.
It is a "File not found" error but when I click the link then it just downloaded th…
-
Really cool project that I tried to recreate. Unfortunately, after testing, the discrete_vae.py gives the following error because of on inplace operation I cannot find:
```
Model is now CUDA!
[TR…
-
Hi! thanks for your beautiful repo!
Recnetly, i have confused by the vqvae reconstruction. The code like below. I just input img and expect to get the same output, but it not. What is the matter with…
-
Include cell codes after this section:
# Set this False if you are on a local machine that has enough memory (this allows you to do the
# lyrics alignment visualization during the upsampling stage…
-
I followed README.MD to create conda env and it was very successful
But when I run
> python jukebox/sample.py --model=5b_lyrics --name=sample_5b --levels=3 --sample_length_in_seconds=20 --total_sam…
-
Hi @rosinality,
Thanks for the code. I want to train the model from scratch on LFW dataset and focus on reconstructions only. Will this code do this and also what are the steps and the hyperparameter…
-
Hello,
I'm wondering if there is any thing need to be changed if I resize images into 128*128?
-
I am trying to implement the VQ-VAE using TensorFlow 2.X.
I borrow the code of the VQ-VAE training from [this github][1] which is written in TF 2x. and I'm working on merging the Keras code of Pixel…