[PR #140] [MERGED] Reduce half of similarity muls after encoding (optimization) #465

Closed
opened 2026-10-31 21:15:15 +00:00 by bsakaguchi · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/openai/CLIP/pull/140
Author: @or-toledano
Created: 8/13/2021
Status: ✅ Merged
Merged: 8/29/2021
Merged by: @jongwook

Base: main ← Head: patch-3


📝 Commits (1)

  • a8aa7cb Reduce half of similarity muls after encoding

📊 Changes

1 file changed (+1 additions, -1 deletions)

View changed files

📝 clip/model.py (+1 -1)

📄 Description

(cAB)^T = c B^T A^T
Saves half of the similarity products in the CLIP model.py after the visual/text encoding stages
Relevant when using a lot of labels / multiple images


🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/openai/CLIP/pull/140 **Author:** [@or-toledano](https://github.com/or-toledano) **Created:** 8/13/2021 **Status:** ✅ Merged **Merged:** 8/29/2021 **Merged by:** [@jongwook](https://github.com/jongwook) **Base:** `main` ← **Head:** `patch-3` --- ### 📝 Commits (1) - [`a8aa7cb`](https://github.com/openai/CLIP/commit/a8aa7cb2657e51771e93d987075c441d57a2640e) Reduce half of similarity muls after encoding ### 📊 Changes **1 file changed** (+1 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `clip/model.py` (+1 -1) </details> ### 📄 Description (cAB)^T = c B^T A^T Saves half of the similarity products in the CLIP model.py after the visual/text encoding stages Relevant when using a lot of labels / multiple images --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
bsakaguchi 2026-10-31 21:15:15 +00:00
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#465
No description provided.