[Export] Keep user-provided dynamic axes #1442
Merged
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
KSGulin
requested review from
markurtz,
DaltheCow and
anmarques
and removed request for
a team
bfineran
approved these changes
Mar 15, 2023
dbogunowicz
approved these changes
Mar 16, 2023
KSGulin
added a commit
that referenced
this pull request
Mar 16, 2023
KSGulin
added a commit
that referenced
this pull request
Mar 16, 2023
KSGulin
added a commit
that referenced
this pull request
Mar 16, 2023
KSGulin
added a commit
that referenced
this pull request
Mar 17, 2023
bfineran
pushed a commit
that referenced
this pull request
Mar 17, 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Outdated suggestions cannot be applied.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.
When exporting models, we currently ignore user-provided dynamic axes argument and instead default to always making batch size dynamic. This overwrites other dynamic inputs, such as image size in yolov5.
The change here preserves the default of always setting the batch size to dynamic and preserves the user/integration input, giving preferences to dynamic batch size.
Test plan
Covered by existing tests
Local test
Running the command below and creating a deepspare pipeline with the resulting model and a custom image size.
sparseml.yolov5.export_onnx --weights zoo:cv/detection/yolov5-l/pytorch/ultralytics/coco/pruned94_quant-none --dynamic