Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

ONNX export update for YOLOv8 #1497

Merged
merged 9 commits into from
Mar 30, 2023
Merged

Conversation

anmarques
Copy link
Member

Adds a function that allows a dequantize node to be propagated down from a split node. That allows the dequantize node to be close to other ops that might be quantized after the split, and enable the proper conversion.

Copy link
Member

@bfineran bfineran left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM overall - will need to add this to the ONNXToDeepSparse converter as well

src/sparseml/onnx/utils/helpers.py Outdated Show resolved Hide resolved
Co-authored-by: Benjamin Fineran <bfineran@users.noreply.github.com>
@anmarques anmarques requested a review from bfineran March 30, 2023 19:43
@anmarques
Copy link
Member Author

LGTM overall - will need to add this to the ONNXToDeepSparse converter as well

Will add ONNXToDeepSparse in a future PR

@anmarques anmarques merged commit 93ba39c into main Mar 30, 2023
@anmarques anmarques deleted the research/yolov8/silu_onnx_export branch March 30, 2023 21:23
@yoloyash yoloyash mentioned this pull request Jun 30, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants