Some Error when trying to TensorRT engine in Python subprocess

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

Error Code:

Using output node Openpose/concat_stage7
Converting to UFF graph
No. nodes: 500
[TensorRT] ERROR: engine.cpp (185) - cuBLAS Error in initializeCommonContext: 1 (Could not initialize cublas, please check cuda installation.)

But I’m sure that CUDA and cudnn have been installed correctly.

root@ubuntu:~/BolaaSmart/TensorRT# nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2019 NVIDIA Corporation
Built on Wed_Apr_24_19:10:27_PDT_2019
Cuda compilation tools, release 10.1, V10.1.168
root@ubuntu:~/BolaaSmart/TensorRT#

bashrc code:
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda-10.1/lib64
export PATH=$PATH:/usr/local/cuda-10.1/bin
export CUDA_HOME=$CUDA_HOME:/usr/local/cuda-10.1
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/root/TensorRT-5.1.5.0/lib

I used CUDA 10.1 + cudnn7.5 + TensorRT 5.1.5, i could not find the cause of the error.

2

I met the same problem.

3

I met the same problem. How did you solve it