TensorRT 6.0 and python

I want to run optimized inference of models built with pytorch e.g. on my desktop. The C++ example /usr/src/tensorrt/samples/sampleMNIST works. I want to try the same example in the python directory. I don’t know how to install tensorrt with pip or conda, so

import tensorrt

fails. I’m a relative newcomer to python.
Here’s the output of uname -a; nvidia-smi -L; rpm -qa | grep -e tensorrt -e python3-libnv

Linux drk 5.4.8-200.fc31.x86_64 #1 SMP Mon Jan 6 16:44:18 UTC 2020 x86_64 x86_64 x86_64 GNU/Linux
GPU 0: GeForce GTX 750 (UUID: GPU-9aff989f-201c-51cb-7db5-dcdae42a7703)
nv-tensorrt-repo-rhel7-cuda10.1-trt6.0.1.5-ga-20190913-1-1.x86_64
python3-libnvinfer-devel-6.0.1-1.cuda10.1.x86_64
python3-libnvinfer-6.0.1-1.cuda10.1.x86_64
tensorrt-6.0.1.5-1.cuda10.1.x86_64

Installing the python bits also installed

python36-3.6.10-1.fc31.x86_64                    @updates

but

/usr/lib64/python3.6/site-packages/tensorrt
/usr/lib/python3.6/site-packages/[empty]

Hi,

As a general solution - if you have nvidia-docker (GitHub - NVIDIA/nvidia-docker: Build and run Docker containers leveraging NVIDIA GPUs) installed, you can easily run all kinds of frameworks and configurations (CUDA 9, 10, 10.1, 10.2) (TensorRT 5, 6, 7) (PyTorch 1.2, 1.3, 1.4), etc. using our NGC containers: Data Science, Machine Learning, AI, HPC Containers | NVIDIA NGC

If you don’t want to use containers and only care about using the TensorRT python API specifically, the tar.gz file installation is probably the easiest method: Installation Guide :: NVIDIA Deep Learning TensorRT Documentation

Just follow the steps to install TensorRT at the link above, then pip installing the tensorrt-*-cp3x-none-linux_x86_64.whl should allow you to do import tensorrt in your python code.

Hi,
I actually figured this out a minute ago. On Fedora31, I installed the tensorrt distro rpm and later installed the python bits from the gz file. I must have messed something up because I had to install the cuda10.1 runtimes for the python bits, whereas the tensorrt distro used 10.2.
But it works!
I’ve tried a bit with docker containers, but I haven’t gotten very far. At some point I am going to be training nn’s on cloud-based gpus.
Thanks!