Hello Sir,
I have Nvidia Jetson Nano (reComputer J1010 -4GB) from SeeedStudio. For my AI project I want to utilize it’s CUDA cores for faster processing. I have tried many methods of installing Torchvision and Pytorch but gpu isn’t utilizing. So kindly help me to install Torchvision, Pytorch with CUDA support. My jetson nano board has Ubuntu 18.04 with Jetpack version 4.6.6 and python support of 3.6
Hello @Saurabh_A
Could you please try the wheels from jp4/cu102 index? Please let us know how the installation and the testing go.
I hope this helps!
Regards!
Eduardo Salazar
Embedded SW Engineer at RidgeRun
Contact us: [email protected]
Developers wiki: https://developer.ridgerun.com/
Website: www.ridgerun.com
1 Like
Sure I will try. But how do I install cuda supported opencv?
Hi @Saurabh_A
You could take a look at Compiling OpenCV from Source for reference.
I hope this helps!
Regards.
I have successfully installed CUDA supported opencv , pytorch and torchvision on jetson nano. But my AI detection model uses YOLOv8. The default python on jetson nano is 3.6.9 which is final official version for jetpack 4.6.6. So in order to use YOLOv8 at least python 3.8 is required to install ultralytcs. Could you please help me in this?
Thank you.
Hello @Saurabh_A
Sorry for the late response. You can take a look at the following topics:
- https://askubuntu.com/questions/682869/how-do-i-install-a-different-python-version-using-apt-get
- https://stackoverflow.com/questions/1534210/use-different-python-version-with-virtualenv
- Miniconda - Anaconda
Hope this helps!
1 Like
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.