-
Hi
Interesting and great work. Can you elaborate a bit about training time for this? How long did it take to pre-train the
VQ-VAE and then the VQ-MAE-S?
Further, in the paper I think there is a…
crzdg updated
7 months ago
-
我请问在训练512x512的时候,是再下采样一次,使用16x16的latent size, 还是把v_patch_nums=(1, 2, 3, 4, 5, 6, 8, 10, 13, 16)扩展为v_patch_nums=(1, 2, 3, 4, 5, 6, 8, 10, 13, 16....32), 还是直接使用v_patch_nums=(1, 2, 3, 4, 5, 6, 8, 10, 13,…
-
Hi! Thank you for the excellent work! I have two questions on the data loader.
- First, when I read the code in the class `TrajectorySlicerDataset`, I found [the code](https://github.com/jayLEE0301/…
-
Thank you for sharing the great work!
I have downloaded the pretrained weights as instructed, and used them to evaluate your proposed method on HumanML3D.
All the numbers seems to be somewhere in …
-
When I try to generate midi from the command:
`python src/generate.py --model figaro --checkpoint ./checkpoints/figaro.ckpt --vae_checkpoint ./checkpoints/vq-vae.ckpt`
The issue can be repeated.
An…
Wietc updated
7 months ago
-
## Keyword: metric learning
### ShufaNet: Classification method for calligraphers who have reached the professional level
- **Authors:** Ge Yunfei, Diao Changyu, Li Min, Yu Ruohan, Qiu Linshan, Xu…
-
I understand that the VQ-VAE used by foldseek translates each amino acid into one of 20 state. (before: VAL amino acid after: ALA amino acid) so is there a way to get pre-trained 3Di embedding before …
-
Hi, thanks for this high-quality codebase.
Recently, I've been utilizing your implemented FSQ functionality, setting the levels to [8, 8, 8, 6, 5]. However, during my testing, I encountered an une…
-
[24.08.2023 12:07:39] jasiu-rozowyczlowiek:
[24.08.2023 12:07:39] jasiu-rozowyczlowiek
-
### Context
Horovod was not working for me. It was getting stuck in variable broadcast step. I have isolated the problem to NCCL/NVLINK. Here are the details. Please help!!
### System Details
- U…