New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Bug in FSQ, with return_indices to False and image-type feature input #139

Open

MisterBourbaki opened this issue Jun 20, 2024 · 0 comments

Contributor

MisterBourbaki commented Jun 20, 2024

The new version of FSQ, with the possibility to not compute indices and return only None, has a small bug:

from vector_quantize_pytorch.finite_scalar_quantization import FSQ
import torch

quantizer = FSQ(levels=[8,5,5,5], return_indices=False)
images = torch.rand(1, 4, 32, 32)

quantizer(images)

the code above will raise a RuntimeError, as Einops try here to unpack None.

I will shortly propose a PR, which solves the issue and clean a bit the code, for better readability and ease of use.

MisterBourbaki mentioned this issue

Fix Issue #139 and refacto of the whole FSQ implementation #140

Closed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment