Added Fine tuning a VLM for Object Detection Grounding using TRL recipe - #315
Conversation
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
|
View / edit / reply to this conversation on ReviewNB merveenoyan commented on 2025-07-17T15:58:52Z you could write bbox format for this dataset (is it xywh or xyxy?) |
|
View / edit / reply to this conversation on ReviewNB merveenoyan commented on 2025-07-17T15:58:52Z not sure of the function name tbh 😅 |
|
View / edit / reply to this conversation on ReviewNB merveenoyan commented on 2025-07-17T15:58:53Z it recognizes two girls, we could just say if we train further it will be better |
merveenoyan
left a comment
merveenoyan
left a comment
There was a problem hiding this comment.
very nice! left only three comments, otherwise LGTM :)
stevhliu
left a comment
stevhliu
left a comment
There was a problem hiding this comment.
Awesome job, really nice to read your notebooks again! 😄
|
Thanks a lot for the comments! ❤️ |
4 participants
What does this PR do?
Adds a new recipe 🧑🍳 for fine tuning a VLM for object detection + visual grounding using TRL.
Fixes #314
Who can review?
@merveenoyan and @stevhliu