'ImportError: No module named 'tensorrt'
I installed TensorRT on my VM using the Debian Installation. If I run "dpkg -l | grep TensorRT" I get the expected result:
ii graphsurgeon-tf 5.0.2-1+cuda10.0 amd64 GraphSurgeon for TensorRT package
ii libnvinfer-dev 5.0.2-1+cuda10.0 amd64 TensorRT development libraries and headers
ii libnvinfer-samples 5.0.2-1+cuda10.0 all TensorRT samples and documentation
ii libnvinfer5 5.0.2-1+cuda10.0 amd64 TensorRT runtime libraries
ii python3-libnvinfer 5.0.2-1+cuda10.0 amd64 Python 3 bindings for TensorRT
ii python3-libnvinfer-dev 5.0.2-1+cuda10.0 amd64 Python 3 development package for TensorRT
ii tensorrt 5.0.2.6-1+cuda10.0 amd64 Meta package of TensorRT
ii uff-converter-tf 5.0.2-1+cuda10.0 amd64 UFF converter for TensorRT package
Yet when I try to import it in python I get:
File "<stdin>", line 1, in <module>
ImportError: No module named 'tensorrt'
What am I doing wrong?
Solution 1:[1]
i had same error, solved it by installing following 2 packages:
# from TensorRT Tar Package ( TensorRT-5.0.2.6/python/ )
pip3 install tensorrt-5.0.2.6-py2.py3-none-any.whl
# pycuda
pip3 install pycuda
# libnvinfer 5.0.2-1
# libnvinfer-dev 5.0.2-1
# libnvinfer-samples 5.0.2-1
# python3-libnvinfer 5.0.2-1
# python3-libnvinfer-dev 5.0.2-1
# tensorrt 5.0.2.6
Solution 2:[2]
just run these commands:
pip install nvidia-pyindex
pip install nvidia-tensorrt
Solution 3:[3]
two suggestions:
- make sure that your TensorRT is added do your path (LD_LIBRARY_PATH)
- if you have both python 2 and python3 installed, check for package installation in pip list and/or pip3 list
Solution 4:[4]
You need to import in python3 environment as you seems to have installed TensorRT for python3. So it does not get import on python2.
Solution 5:[5]
If you are in a virtual environment, go to the following path to check if it exists.
(deepNN) agxxavier@agxxavier-desktop:~/miniforge3/envs/deepNN/lib/python3.6/site-packages$ ls
Use the following command to check where tensorrt.so is located
(base) agxxavier@agxxavier-desktop:~$ sudo find / -iname "*tensorrt*"
and to create a soft connection in your virtual environment.
(deepNN) agxxavier@agxxavier-desktop:~/miniforge3/envs/deepNN/lib/python3.6/site-packages$ ln -s /usr/lib/python3.6/dist-packages/tensorrt/tensorrt.so tensorrt.so
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|---|
| Solution 1 | sailfish009 |
| Solution 2 | Sajjad Aemmi |
| Solution 3 | Pidem |
| Solution 4 | VARAT BOHARA |
| Solution 5 | user11323925 |
