mirror of
https://github.com/openai/CLIP.git
synced 2026-11-05 01:37:26 +00:00
[GH-ISSUE #269] How to train CLIP from scratch？ #235
Labels
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
openai/CLIP#235
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @newbietuan on GitHub (Jul 20, 2022).
Original GitHub issue: https://github.com/openai/CLIP/issues/269
Hi, Thanks for the great work.
Due to the needs of specific tasks, i want to train CLIP from scratch without using BPE coding and the length limit of 77, how should i do?
about length_limit, it seems that is ok not to use simple_tokenizer.py, so the mainly problem is how to train CLIP from scratch？
Very thanks.
@jinghaoliu commented on GitHub (Jul 25, 2022):
It seems that OpenAi doesn't provide a code that can train CLIP from scratch. You could refer to the codebase.https://github.com/mlfoundations/open_clip Hope that is helpful for you.