Ensure ONNX model generation considers opset version #682
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
This commit modifies the `gen_processing_models` function in `onnxruntime_extensions/cvt.py` to explicitly include the `opset_version` argument when calling `make_onnx_model` for both pre-processing and post-processing graphs. Previously, the function only generated models if `pre_g` or `post_g` existed, without specifying the opset version. This update ensures that generated ONNX models adhere to the desired opset level, improving compatibility and deployment options.
wenbingl
approved these changes
Mar 27, 2024
|
/azp run onnxruntime-extensions.CI |
|
Azure Pipelines successfully started running 1 pipeline(s). |
wenbingl
reviewed
Mar 27, 2024
| return make_onnx_model(pre_g) if pre_g else None, \ | ||
| make_onnx_model(post_g) if post_g else None | ||
| return make_onnx_model(pre_g, opset_version=opset) if pre_g else None, \ | ||
| make_onnx_model(post_g, opset_version=opset) if post_g else None |
There was a problem hiding this comment.
it looks like it also need some fixing for the case of opset==None, check CI pipeline result for more details. Would you like to do that, or wait for my help?
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Outdated suggestions cannot be applied.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.
This PR modifies the
gen_processing_modelsfunction inonnxruntime_extensions/cvt.pyto explicitly include theopset_versionargument when callingmake_onnx_modelfor both pre-processing and post-processing graphs.Previously, the function only generated models if
pre_gorpost_gexisted, without specifying the opset version. This update ensures that generated ONNX models adhere to the desired opset level, improving compatibility and deployment options.