Stack Overflow
Stack Overflow

Questions tagged [nvidia-jetson]

Nvidia Jetson is Nvidia's family of embedded devices, targeted for computing on the edge by users desiring to run machine learning and artificial intelligence tasks.

Use this tag for questions about programming specifically for the Jetson devices, namely: the Nano, TX1, TX2(i), or AGX. Please also tag the language you are coding in and the frameworks you are using for context.

Visit Nvidia's official site for more information on the Jetson devices.

405 questions
4
votes
1 answer

how to run a 5v stepper motor on jetson nano

I tried running a 5v stepper motor using RPI code on jetson nano and it gives me ValueError: The channel sent is invalid on a JETSON_NANO Board I have installed jetson gpio and still giving me same error but the code works fine on raspberry…
genesis mendoza
  • 63
  • 1
  • 6
4
votes
3 answers

How to import cv2 on Jetson nano under a virtualenv?

If you aren't using a virtualenv, the cv2 module is imported successfully nano@nano:~$ python3 Python 3.6.7 (default, Oct 22 2018, 11:32:17) [GCC 8.2.0] on linux Type "help", "copyright", "credits" or "license" for more information. >>> import…
Jonathan Tse
  • 875
  • 1
  • 9
  • 14
3
votes
1 answer

Calling Python through ssh in Python script causes "Illegal instruction (core dumped)"

I have a Python script call.py to log in to another machine through ssh and execute another Python script saved on this machine, something like this # call.py import os # log into user@host machine and execute python script os.system("sshpass -p…
Otter_warrior
  • 193
  • 1
  • 12
3
votes
0 answers

How to convert tensorflow model to TensorRT

I am looking for end-to-end tutorial, how to convert my trained tensorflow model to TensorRT to run it on Nvidia Jetson devices. I know how to do it in abstract (.pb -> ONNX - > [Onnx simplifyer] -> TRT engine), but I'd like to see how other do It,…
Pavlo Sharhan
  • 174
  • 2
  • 10
3
votes
1 answer

Image's rootfs is incomplete while building from Dockerfile

I'm building an image for Jetson from a Dokerfile. Here's an excerpt from it: FROM nvcr.io/nvidia/l4t-pytorch:r32.4.4-pth1.6-py3 # some installation RUN ls -l /usr/local/cuda-10.2/targets/aarch64-linux/lib/ # more installation The ls command…
Alexander R.
  • 31
  • 4
3
votes
2 answers

Nvidia flash.sh file not found in ubuntu 18

I want to create an image from nvidia jetson tx2, in several places (like https://developer.ridgerun.com/wiki/index.php?title=Cloning_TX2) talk about flash.sh file to perform the task but I cannot found it, also I search using find / -iname flash.sh…
cflorenciav
  • 419
  • 1
  • 6
  • 16
3
votes
2 answers

Torchscript vs TensorRT for real time inference

I have trained an object detection model to be used in production for real-time applications. I have the following two options. Can anyone suggest what is the best way to run inference on Jetson Xavier for best performance? Any other suggestions are…
Akshay Kumar
  • 277
  • 2
  • 11
3
votes
1 answer

psplash-write does not work when psplash is started from the init script (PID=1)

I have integrated psplash to a custom Yocto layer for NVIDIA Jetson Nano. I want to run psplash from the very first init script (PID=1). The reason is to cover the time spent by systemd to load unit and service files. I have added…
mozcelikors
  • 2,582
  • 8
  • 43
  • 77
3
votes
0 answers

PyTorch list slicing on GPU slower than on CPU

I would like to optimize ML code (SSD in PyTorch) on NVIDIA Jetson Xavier NX (development kit). One of the bottlenecks seems to be list slicing on PyTorch (1.6.0) tensors on GPU device. The same problem occured on NVIDIA GeForce GTX 1050 Ti (GP107),…
Petr Dvořáček
  • 123
  • 6
3
votes
1 answer

Push OpenCV mat inside a DeepStream pipeline

I would like to open a video stream by OpenCv and push frame by frame inside a DeepStream pipeline to use tesornRT to make an inference on Yolov3 model, but i do not know how to make it works. I'm trying to follow the directives that I found here,…
Neorem
  • 71
  • 4
3
votes
2 answers

Tensorflow Lite on Nvidia Jetson

Has anyone used Tensorflow Lite on any Nvidia Jetson product? I want to use my Jetson Nano for inference and would like to so with tf-lite utilizing the GPU. Confusingly, there does not seem to be a Python API for creating a GPU Delegate in…
Syd Shore
  • 41
  • 1
  • 3
3
votes
1 answer

How to include OpenCV in pyinstaller when opencv is installed from source?

I have installed OpenCV 4.1 in Jetson Nano from source. It works perfect when i run my python3 code. After compiling python code using pyinstaller it throws ImportError. ImportError: OpenCV loader: missing configuration file: ['config.py']. Check…
Krunal Sonparate
  • 1,122
  • 10
  • 29
3
votes
0 answers

unsupported operation _FusedBatchNormV3 with tensorRT and jetson tx2

On a Jetson TX2 I am running: Linux4Tegra R32.2.1 UFF Version 0.6.3 TensorRT 5.1.6.1 Cuda 10 Python 3.6.8 I get this error message: [TensorRT] ERROR: UffParser: Validator error: sequential/batch_normalization_1/FusedBatchNormV3: Unsupported…
Patty Eckhart
  • 31
  • 1
3
votes
0 answers

(Argus) Error EndOfFile and Error InvalidState during jetson nano camera opencv tests

I'm trying to test out my Pi Camera on my Jetson Nano. Simple tests run smooth but running this python code edited to have the videoCapture argument of a gstreamer_pipeline instead of just '0'. This code however, only works once. When closing it…
Varyag
  • 676
  • 12
  • 29
3
votes
2 answers

How do i patch in yocto?

I am attempting to build an image for the jetson-nano using yocto poky-warrior and meta-tegra warrior-l4t-r32.2 layer. I've been following this thread because he had the same problem as me, and the answer on that thread fixed it, but then a new…
Varyag
  • 676
  • 12
  • 29
1
2
3
…
26 27