I don’t know how that article installs it, but I would recommend trying the l4t-pytorch container for a compatible version of JetPack-L4T that you are running and seeing if the performance is different using the container, because those images come with PyTorch/torchvision already installed and tested using the wheels from this post.
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
Jetson nano slow cuda times with pytorch | 14 | 1051 | October 11, 2023 | |
Jetson nano sometimes extremely slow with GPU | 7 | 1095 | November 3, 2023 | |
Jetson nano GPU is not working? | 5 | 1847 | October 15, 2021 | |
How to run pytorch custom inference on Jetson Nano's GPU? | 4 | 1171 | June 21, 2022 | |
Pytorch with jetpack 4.2 works slowly than 3.3 | 6 | 1367 | October 18, 2021 | |
Slow CUDA Loading&Initialisation / GPU Warmup issue | 7 | 1323 | July 21, 2023 | |
Problem with loading models into cuda device (Jetson Nano) | 3 | 760 | December 29, 2021 | |
Why is torch.tensor.to('cuda') so slow? | 5 | 71 | December 9, 2024 | |
Jetson Nano slow CUDA performance vs CPU | 6 | 833 | February 26, 2024 | |
Cant install Pytorch on JetsonNano P3450 | 21 | 2488 | August 16, 2023 |