Failed to run tensorrt sample with python API with the GPU GeForce 1050Ti

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

Description

  1. Failed to run tensorrt python samples with the GPU GeForce gtx 1050Ti, However it works fine with C++ samples
  2. successfully run the same tensorrt python sample and C++ sample with GPU GeForce RTX 2080Ti via a saved docker from 1

occurred error:
[TensorRT] ERROR: …/rtSafe/safeContext.cpp (105) - Cudnn Error in initializeCommonContext: 1 (Could not initialize cudnn, please check cudnn installation.)

Environment

TensorRT Version: 7.0.0.11
GPU Type: GeForce gtx 1050Ti
Nvidia Driver Version: 410.78
CUDA Version: 10.0
CUDNN Version: 7.6.5
Operating System + Version: ubuntu 16.04
Python Version (if applicable): 3.7.1
TensorFlow Version (if applicable): none
PyTorch Version (if applicable): 1.4.0
Baremetal or Container (if container which image + tag): Lenovo Thinkpad X1 Extreme

Relevant Files

Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)
https://developer.nvidia.com/compute/machine-learning/tensorrt/secure/7.0/7.0.0.11/tars/TensorRT-7.0.0.11.Ubuntu-16.04.x86_64-gnu.cuda-10.0.cudnn7.6.tar.gz

Steps To Reproduce

  1. install cuda10.0, cudnn7.6.5, tensorrt 7.0.0.11
  2. run sample in TensorRT-7.0.0.11/samples/python/network_api_pytorch_mnist

Please include:

  • Exact steps/commands to build your repro
  • Exact steps/commands to run your repro
  • Full traceback of errors encountered
2

Hi @huangheqingbit,
This error is likely due to either (1) mismatched versions of libraries/dependencies, or (2) sometimes this can happen due to Out Of Memory (OOM) errors.
We recommend you to try the same on NGC containers to avoid system dependency related issues.
Thanks!