[Fix] Prevent RuntimeError in ONNX export with empty input in ONNXNMSRotatedOp #2305
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Outdated suggestions cannot be applied.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.
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily receiving feedbacks. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.
Motivation
This PR addresses a runtime error that occurs when exporting ONNX with dummy data (i.e., when no objects are present). Specifically, the issue arises from the
ONNXNMSRotatedOp
class in thenms_rotated.py
file.The problem was that when no objects were detected (resulting in
indices
being empty), aRuntimeError
occurred whentorch.cat(indices)
was called. To resolve this issue, I added a condition to check the length ofindices
before concatenating. Ifindices
is empty, it now returns a tensor of zeros with the appropriate shape, datatype, and device settings.Modification
BC-breaking (Optional)
Does the modification introduce changes that break the backward-compatibility of the downstream repositories?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.
Use cases (Optional)
If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.
Checklist