Vs 2019 configuration tensorrt

To configure TensorRT

1、 download TensroRT： link ：https://developer.nvidia.com/nvidia-tensorrt-8x-download

2、 Unzip the downloaded file , And will TensorRT Medium include File move to CUDA Under folder include in , And will TensortRT In the document lib Medium dll And lib The documents are placed in cuda Medium bin And lib\x64 In the folder

3、 install TensorRT, Install these four files separately

pip install tensorrt-8.2.5.1-cp37-none-win_amd64.whl

4、 download cudnn64_8.dll, And put the file in
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.1\bin Under the table of contents

5、 Run code

import torch
import tensorrt as trt

print(trt.__version__)
print(torch.cuda.is_available())

6、 Run the example , Modify the designated place

7、 download cudnn：https://developer.nvidia.com/rdp/cudnn-download, Copy the files under the three folders to NVIDIA GPU Computing Toolkit Under the corresponding folder

8、 download zlibwapi.dll file , And put the file in system32 Under the folder , Running results

If there is a mistake , Please correct me. （ thank you ）