Ensure ONNX model generation considers opset version

microsoft / onnxruntime-extensions

onnxruntime-extensions: A specialized pre- and post- processing library for ONNX Runtime

MIT License

295 stars 80 forks source link

Ensure ONNX model generation considers opset version #682

Open kazssym opened 3 months ago

kazssym commented 3 months ago

This PR 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 commented 3 months ago

/azp run onnxruntime-extensions.CI

azure-pipelines[bot] commented 3 months ago

Azure Pipelines successfully started running 1 pipeline(s).