I've already created a Model.onnx file, how can I convert in to .hex format to make prediction by SQL Script in Azure Synapse? I read this document but still can't understand how to do it. Can anyone explain?

CodePudding user response：

Train a model in synapse studio which includes machine learning libraries and apache spark. Here the major requirement is to make ONNX supportive create, register and use model.

We can deploy the ONNX model to a table in SQL database pool using Synapse studio which leads to implement complete ONNX deployment using Synapse studio without coming out of that environment and using the notebook within the environment. Please Checkout the repository .

For more information refer this link.

CodePudding user response：

To convert a Model.onnx file to the .hex format for use in Azure Synapse, you can use the ONNX Runtime onnxruntime_convert tool. This tool allows you to convert ONNX models to various formats, including the .hex format used by Azure Synapse.

To use the onnxruntime_convert tool, you will need to install ONNX Runtime on your machine. You can do this using pip:

pip install onnxruntime

Once ONNX Runtime is installed, you can use the onnxruntime_convert tool to convert your Model.onnx file to the .hex format as follows:

onnxruntime_convert -f hex -i Model.onnx -o Model.hex

This will create a new file called Model.hex that contains the converted model in the .hex format. You can then use this file in Azure Synapse to make predictions using SQL scripts.