-
what is the codebook size / vocab size for encoded snac data for the various models?
-
Hi. Thanks for the great work. I have two questions.
1. Can you please clarify what the second `1` is used for?
`codebook_size` is `1024`, so its indices are between `[0, 1023]`. The first `1` in …
-
Hi all,
I noticed that using `ResidualVQ` as:
```
ResidualVQ(
dim=Z_CHANNELS, # 512
num_quantizers=NUM_QUANTIZERS, # 2
codebook_size=CODEBOOK_SIZE, # 1…
-
The codebook of the "Elections" dataset is messed up. Some variables do not correspond to the description, some variables in the data do not appear in the codebook, and variables in the codebook are n…
-
你好,非常感谢你的工作,我想请教一下在训练Dynamic Visual Tokenizer 时有出现code collapse现象么?在这个过程中reconstruction loss最后会收敛到什么数值呀?
sijeh updated
1 month ago
-
It's possible that I'm missing something due to unfamiliarity with the codebase, but it looks to me like vpq_dataset and train_pq are collapsing all the subspaces into a single codebook. E.g. if you …
-
还有另一个问题,代码中使用的CLIP权重是在224*224的图片分辨率下训练的,这种情况下使用clip获取的codebook,适用于512*512的图片重建吗
-
Hello,
Congratulations on the successful development of the SEED model! I am impressed by its ability and wanna to reproduce it locally. However, I am encountering some confusing problems. The config…
-
https://github.com/josephbergevin/codebook-md/blob/5ebb4089a05705d4c6d359a6d3c3e117d2c74ddf/package.json#L64-L68
-
there is an error when trying to load the model
the error is in the model itself checkpoint = torch.load(local_embedding_path, map_location="cpu")['weight']
this apparently expects embed_ll…