Getting error for tensorrt module not found

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

while working with trt pose repository " GitHub - NVIDIA-AI-IOT/trt_pose: Real-time pose estimation accelerated with NVIDIA TensorRT "
getting error while running command : sudo python3 setup.py install

error : ModuleNotFoundError: No module named ‘tensorrt’.

I tried installing tensorrt with this command : “pip install nvidia-pyindex
pip install nvidia-tensorrt” and its installed “nvidia-tensorrt-99.0.0 and tensorrt-8.6.1”.

But after this also it is throwing the same error that no module named tensorrt.

VM specifications for your reference : NVIDIA-SMI 525.85.12 Driver Version: 525.85.12 CUDA Version: 12.0

what is the correct version of tensorrt that i need to install with this vm specification and what is the command for the installation.

2

Hi,

Please checkout Support Matrix :: NVIDIA Deep Learning TensorRT Documentation.

Also, we recommend you follow the installation guide.

Thank you.

3

To setup dGPU in Ubuntu 20.04 on Nvidia T4 machine
https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Quickstart.html

  1. sudo apt-get update

  2. Install Dependencies
    sudo apt install
    libssl1.1
    libgstreamer1.0-0
    gstreamer1.0-tools
    gstreamer1.0-plugins-good
    gstreamer1.0-plugins-bad
    gstreamer1.0-plugins-ugly
    gstreamer1.0-libav
    libgstreamer-plugins-base1.0-dev
    libgstrtspserver-1.0-0
    libjansson4
    libyaml-cpp-dev
    libjsoncpp-dev
    protobuf-compiler
    gcc
    make
    git
    python3

  3. Install CUDA Toolkit 11.8
    sudo apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub
    sudo add-apt-repository “deb Index of /compute/cuda/repos/ubuntu2004/x86_64 /”
    sudo apt-get update
    sudo apt-get install cuda-toolkit-11-8

  4. Install NVIDIA driver 525.85.12
    wget https://us.download.nvidia.com/tesla/525.85.12/NVIDIA-Linux-x86_64-525.85.12.run
    chmod 755 NVIDIA-Linux-x86_64-525.85.12.run
    sudo ./NVIDIA-Linux-x86_64-525.85.12.run --no-cc-version-check

  5. Install PyTorch
    Start Locally | PyTorch
    pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118

  6. Install tensorrt
    Installation Guide :: NVIDIA Deep Learning TensorRT Documentation
    a. wget https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/secure/8.6.1/tars/TensorRT-8.6.1.6.Linux.x86_64-gnu.cuda-12.0.tar.gz
    b. tar -xzvf TensorRT-8.6.1.6.Linux.x86_64-gnu.cuda-12.0.tar.gz
    c. cd TensorRT-8.6.1.6/lib
    d. pwd → output (/home/mastekinnovation/TensorRT-8.6.1.6/lib)
    e. export LD_LIBRARY_PATH=/home/mastekinnovation/TensorRT-8.6.1.6/lib
    f. cd TensorRT-8.6.1.6/python
    g. python3 -m pip install tensorrt-8.6.1-cp38-none-linux_x86_64.whl
    h. cd TensorRT-8.6.1.6/uff
    i. python3 -m pip install uff-0.6.9-py2.py3-none-any.whl
    j. cd TensorRT-8.6.1.6/graphsurgeon
    k. python3 -m pip install graphsurgeon-0.4.6-py2.py3-none-any.whl
    l. cd TensorRT-8.6.1.6/onnx_graphsurgeon
    m. python3 -m pip install onnx_graphsurgeon-0.3.12-py2.py3-none-any.whl

  7. Install torch2trt
    GitHub - NVIDIA-AI-IOT/trt_pose: Real-time pose estimation accelerated with NVIDIA TensorRT
    git clone GitHub - NVIDIA-AI-IOT/torch2trt: An easy to use PyTorch to TensorRT converter
    cd torch2trt
    sudo python3 setup.py install --plugins

At this point we are getting “tensorrt module not found”
Please help

tensorrt

4

Hi,
Please refer to the installation steps from the below link if in case you are missing on anything

Also, we suggest you to use TRT NGC containers to avoid any system dependency related issues.

Thanks!