[GH-ISSUE #193] Different accuracy for different batch sizes #166

Open
opened 2026-10-31 21:11:55 +00:00 by bsakaguchi · 0 comments
Owner

Originally created by @harryfin on GitHub (Dec 6, 2021).
Original GitHub issue: https://github.com/openai/CLIP/issues/193

The different accuracies occur when the model is tested with different batch sizes.
I assume it is related to Batch Normalization, even though the model has been set to evaluation mode before testing.

Used Model: 'RN50'

Is there a known solution to this problem?

Originally created by @harryfin on GitHub (Dec 6, 2021). Original GitHub issue: https://github.com/openai/CLIP/issues/193 The different accuracies occur when the model is tested with different batch sizes. I assume it is related to Batch Normalization, even though the model has been set to evaluation mode before testing. Used Model: 'RN50' Is there a known solution to this problem?
Sign in to join this conversation.
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
openai/CLIP#166
No description provided.