ValueError: This ORT build has [

报错内容：

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'], ...)

问题描述：在使用onnxruntime构建会话框时，出现了如上报错。

import onnxruntime as ort 
import torch 
import onnx 
import numpy as np 

# 加载模型
model = onnx.load("./resnet18.onnx")
# 检查模型
onnx.checker.check_model(model)

# 1. 开启会话
session = ort.InferenceSession("./resnet18.onnx")
x = np.random.randn(1,3,224,224).astype(np.float32) # 输入的类型必须是numpy float32 

outputs = session.run(None, input_feed={"input" : x})
print(outputs.shape)

解决方案：

# 1. 开启会话
session = ort.InferenceSession("./resnet18.onnx", providers=['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider'])