在使用onnxruntime GPU版本做推理测试时，出现了如下的错误：

Traceback (most recent call last):File "D:\cv\ConNext_demo\testonnx.py", line 57, in <module>rnet1 = ONNXModel(onnx_model_path)File "D:\cv\ConNext_demo\models\onnx.py", line 7, in __init__self.onnx_session = onnxruntime.InferenceSession(onnx_path)File "D:\ProgramData\Anaconda3\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 335, in __init__self._create_inference_session(providers, provider_options, disabled_optimizers)File "D:\ProgramData\Anaconda3\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 361, in _create_inference_sessionraise ValueError("This ORT build has {} enabled. ".format(available_providers) +
ValueError: This ORT build has ['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider'] enabled. Since ORT 1.9, you are required to explicitly set the providers parameter when instantiating InferenceSession. For example, onnxruntime.InferenceSession(..., providers=['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider'], ...)

解决办法：
将

onnxruntime.InferenceSession(onnx_path)

改为：

 onnxruntime.InferenceSession(onnx_path,providers=['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider'])