-
Notifications
You must be signed in to change notification settings - Fork 664
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
No module named 'tensorrt' #152
Comments
Remember to download tensorrt first if you haven't, and make sure it's accessible in your python env or virtualenv https://docs.nvidia.com/deeplearning/sdk/tensorrt-install-guide/index.html |
@bfortuner very thanks!it work. |
it just entry python folder .python setup.py install |
@mathpopo Hi, I noticed that you have run |
Sorry for the naive question. I am facing a similar error. I have successfully installed tensorrt following the steps listed here - https://docs.nvidia.com/deeplearning/sdk/tensorrt-install-guide/index.html (debian installation, verified cuda version and so on, installation succeeds as per the steps listed in the guide up until grp). As far as adding path in environment is concerned, I am setting pythonpath to /usr/lib/python3.6/dist-packages (as per this link - http://www.bojankomazec.com/2019/12/how-to-install-tensorrt-python-package.html). However, the error still persists :(, when trying to import tensorrt. Thanks for your help. |
for me this worked: |
i ran this command and got an error: no space left on device, how can i solve this |
|
git clone https://github.com/NVIDIA-AI-IOT/torch2trt
cd torch2trt
sudo python setup.py install
complete this,run ./test.sh TEST_OUTPUT.md
from .torch2trt import *
ModuleNotFoundError: No module named 'tensorrt'
The text was updated successfully, but these errors were encountered: