Error : 'FAIL : Load model from xxx failed:/onnxruntime_src/onnxruntime/core/graph/model_load_utils.h:47 void onnxruntime::model_load_utils::ValidateOpsetForDomain(const std::unordered_map<std::basic_string<char>, int>&, const onnxruntime::logging::Logger&, bool, const string&, int)

Do the ONNX model quantization, after running the command python -m onnxruntime.quantization.preprocess --input xxx.onnx --output xxx-infer.onnx to preprocess my onnx model, the generated model xxx_infer.onnx cannot be loaded for the following quantization, it returns the error:
FAIL : Load model from onnx_path failed:/onnxruntime_src/onnxruntime/core/graph/model_load_utils.h:47 void onnxruntime::model_load_utils::ValidateOpsetForDomain(const std::unordered_map<std::basic_string, int>&, const onnxruntime::logging::Logger&, bool, const string&, int) ONNX Runtime only guarantees support for models stamped with official released onnx opset versions. Opset 3 is under development and support for this is limited. The operator schemas and or other functionality may change before next ONNX release and in this case ONNX Runtime will not guarantee backward compatibility. Current official support for domain ai.onnx.ml is till opset 2
Any help will be appreciated.

Start by reproducing the preprocessing command python -m onnxruntime.quantization.preprocess with the affected ONNX model and inspect the resulting model's opset metadata. Read the reported onnxruntime/core/graph/model_load_utils.h:47 validation path and determine what model or version details are needed to make the subsequent quantization load successfully; done means the failure is reproducible and the supported configuration or required change is documented.