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
0
votes
1 answer

How can I save a docker image without having enough storage on my main drive?

My problem: I'm trying to save a Jetson TX2 docker image that's about 8GB. The OS and other files+OS are taking up around 21GB meaning I only have about 3GB of storage on the machine. I have already pruned old images and containers, and cannot…
Osi
  • 406
  • 3
  • 13
0
votes
0 answers

Color filtering with dependencies between colors

My current goal is to make a color filter (threshold maybe) that creates a mask for regions with something like the following relations: B < G G > 128 R > 1.5 * G I created such an algorithm already, but it loops through every pixel of the image…
kremerf
  • 21
  • 5
0
votes
2 answers

Transparency for the child widget in Qt5

I use Nvidia Jetson Nano with Linux for Tegra (Ubuntu 18, X11 window system), Python 3.6 and PyQt5. I want to place a transparent widget (or with a transparent background) over the main widget. When these widgets are created as independent…
lich.mk
  • 71
  • 1
  • 5
0
votes
0 answers

TensorRT + PyInstaller on Nvidia Jetson Nano. Deserialize engine causes Cuda Error in loadKernel: 3 (initialization error)

I have a code reading a serialized TensorRT engine: import tensorrt as trt import pycuda.driver as cuda cuda.init() device = cuda.Device(0) context = device.make_context() logger = trt.Logger(trt.Logger.INFO) with trt.Runtime(logger) as runtime: …
Kroshka Kartoshka
  • 1,035
  • 5
  • 23
0
votes
0 answers

How to measure ONLY the inference time in the GPU, using TensorRT and PyCUDA?

I want to measure ONLY the inference time in the Jetson TX2. How can I improve my function to do that? As right now I am measuring: the transfer of the image from CPU to GPU transfer of results from GPU to CPU the inference Or is that not…
Aizzaac
  • 3,146
  • 8
  • 29
  • 61
0
votes
0 answers

GPIO Permission issue Nvidia Jetson AGX Xavier

Good afternoon everyone, When trying to control a stepper motor through the GPIO header on the AGX Xavier I ran into the following issue: When utilizing the jetson-gpio library for python compatible GPIO control I am able to run all sample scripts…
ruudscheenen
  • 34
  • 7
0
votes
2 answers

Pytorch NLP model doesn’t use GPU when making inference

I have a NLP model trained on Pytorch to be run in Jetson Xavier. I installed Jetson stats to monitor usage of CPU and GPU. When I run the Python script, only CPU cores work on-load, GPU bar does not increase. I have searched on Google about that…
redrussianarmy
  • 41
  • 1
  • 8
0
votes
1 answer

GPU TensorFlow for Jetpack 4.4

I would like to ask one thing about the newest Nvidia release of Jetpack OS 4.4. When I click here for looking a release versions in v42 and v43 it has two folders tensorflow and tensorflow-gpu for cpu and gpu version. But when I click v44 it has…
Marcel Kopera
  • 304
  • 2
  • 9
0
votes
1 answer

h5py problem with Docker and Tensorflow on Nvidia Jetson

I am currently trying to build a docker container which should be able to run GPU accelerated tensorflow on top of a Xavier AGX. My approach is derived from example and the official nvidia documentation jetson-tensorflow. My Dockerfile looks like…
Domi
  • 61
  • 4
0
votes
1 answer

DeepStream python apps in custom application

In this link, we can access to gstreamer pipeline buffer and convert the frame buffers in numpy array, I want to know, How I can to accesses the frame buffers in GPU mem and then feed into my custom processor without convert frames into numpy…
DeeeepNet
  • 347
  • 3
  • 11
0
votes
1 answer

Colcon can't find right opencv version

This is on Ubuntu 18.04 running ROS2 Dashing. I built OpenCV from source, and did the ldconfig thing. But colcon keeps trying to use a different version. The error is "missing: opencv_cudaarithm opencv_cudafilters": Whole error…
Oren Bell
  • 460
  • 1
  • 5
  • 13
0
votes
1 answer

Capture image with V4L2 on jetson TX2

To explain my process, find below a diagram: I am working on computed tomography scanner. I use jetson TX2 for image acquisition and pre-processing. From the jetson, I control the turn table and the camera. The camera is the FSM-IMX304m. I need to…
user13162349
0
votes
0 answers

Re-installing OpenCV on Jetson Nano

I am currently working on a Nvidia Jetson Nano. When I installed JetPack 4.4, OpenCV 4.1.1 was included inside and when I was running on my Nano's Python shell, I was able to at least run import cv2 and a few other functions without errors. However,…
Goh Jia Yi
  • 329
  • 3
  • 16
0
votes
1 answer

How do I run Python scripts automatically on Jetson TX2?

I tried crontab -e. @reboot python3 /home/hyebin/project/tensorrt_demos/trt_ssd.py --model ssd_mobilenet_v2_face --usb --vid 1 --width 1280 --height 780 1.Do I just have to add it to the bottom line of the crontab -e? 2. Is it okay to have…
hyebin
  • 5
  • 3
0
votes
1 answer

Error in Cmake "The CUDA compiler identification is unknown" while creating the docker build

I am trying to create a docker build in Xavier. When I run my piece of code without docker it works smooth and I got The CUDA compiler identification. But when I am trying to make a build with dockerfile it gave me an error of CUDA compiler…
chirag
  • 523
  • 7
  • 13
1 2 3
…
26 27