-
-
The result in this work is amazing and I'm very interested in the building reconstruction.
I try to train the vqvae and sdfusion models on the BuildingNet dataset, but the related scripts or configs …
-
Greetings!
Thank you for releasing this repo. We were trying to do an inference using the GPU (JukeBox) version on an EDM dataset of ours. We rent a bare-metal machine on [Featurize](https://featur…
-
-
Hi, thanks for this attractive work!
I met the NaN problem when evaluating the VQVAE. And I found this is caused by the HumanML3D data that contains some NaN motion data.
However, I didn't see …
qrzou updated
9 months ago
-
Dear Developer,
I hope this message finds you well.
I encountered some errors while running your project. Here are the details:
Computer Information:
Total VRAM: 16376 MB
Total RAM: 32387…
-
Hi there.
I am trying to reuse the VQ-VAE, with 118 44.1khz 16bit audio files on a 1080 TI.
executing this:
mpiexec -n 1 python jukebox/train.py --hps=vqvae,small_prior,all_fp16,cpu_ema --name=pr…
-
This issue relates to how we embed each (16x16) patch. Additionally, we discuss the positional encodings we add to each patch's embedding.
# Patch Embedding
Let's review, we split the images in…
-
Hello, I wrote a script based on the demo_sample.ipynb to generate 50,000 samples and tested them using OpenAI's FID evaluation toolkit. However, I found that the metrics did not align. Could you help…
LiCHH updated
1 month ago
-