Add sam ONNX export #995
Closed
Add sam ONNX export #995
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
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. |
fxmarty
force-pushed
the
sam-onnx-export
branch
from
20a34b6 to
17b63a5
Compare
fxmarty
force-pushed
the
sam-onnx-export
branch
from
17b63a5 to
598865e
Compare
|
Closing as #1025 got merged |
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Outdated suggestions cannot be applied.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.
As per title. For now only support
input_pointsas an input, will the rest really be useful @younesbelkada ?We will need an other PR to be merged in transformers huggingface/transformers#22915, and we will need to wait for transformers to release.
Yon can try with:
optimum-cli export onnx --model fxmarty/sam-vit-tiny-random sam_onnxValidation on various shapes pass:
RUN_SLOW=1 pytest tests/bettertransformer/test_encoder.py -k "test_accelerate_compatibility_cpu_gpu" -s -vvvvvFixes #990