[Docs / SAM ] Reflect correct changes to run inference without OOM
#27268
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
younesbelkada
changed the title
Docs / ] Docs / SAM ] Reflect correct changes to run inference with OOM
4 tasks
younesbelkada
changed the title
Docs / SAM ] Reflect correct changes to run inference with OOM Docs / SAM ] Reflect correct changes to run inference without OOM
amyeroberts
approved these changes
Nov 3, 2023
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. |
EduardoPach
pushed a commit
to EduardoPach/transformers
that referenced
this pull request
Nov 19, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Fixes #27266
One needs to always wrap the model forward pass to avoid OOM issues for SAM forward pass. In the orignal modeling code they force-use
torch.no_grad()context manager in the forward pass: https://github.com/facebookresearch/segment-anything/blob/main/segment_anything/modeling/sam.py#L53 - but we avoid that since we also support SAM fine-tuning.Check out my comment here for more details: #27266 (comment)
cc @amyeroberts