facebookresearch / facebookresearch/MetaCLIP

I find a bug in your source code.

Open
#96 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
1.9k
Forks
80
PR merge metrics
No merged PRs in 30d

Description

Image

In your default setting, "gpu_trans" is True. but training preprocessor uses "gpu_trans=True" and eval preprocessor uses "gpu_trans=False".
So data' range is different from training phrase and eval

By the way, model.forward has no operation to normalize data range for training phrase, so is is a big bug

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.