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
1
vote
0 answers

Memory issue while trying to convert it to tensorrt or tflite

I succesfull converted the .weight file to .tf file, then i used the convert_trt.py scirpt which indeed is getting killed after a 2 mins wait. I use a Jetson Xavier nx, Cuda 10.2. Error log: .. .. . 2020-08-22 15:31:22.362558: I…
Sai Krishnadas
  • 2,863
  • 9
  • 36
  • 69
1
vote
1 answer

Nvidia Jetson Tx2 Opencv Compiling in Docker

Hi I have several times compiled opencv in my host machine or several arm based system before. As all you now on arm based system compiling opencv takes longer time so I used Quemu to virtualized x86 processor to arm64 and I pulled nvidia jetpack…
emir
  • 70
  • 8
1
vote
0 answers

Is there a way to cross-compile tensorflow-2 for nvidia jetson boards (AGX, TX2)

I found a guide for compiling tensorflow-1.5 with CUDA support for TX1, https://jany.st/post/2018-02-05-cross-compiling-tensorflow-for-jetson-tx1-with-bazel.html Is there a way to do the same for tf-2? I want to install a fork of tf-2 on my AGX…
yaswanth89
  • 56
  • 5
1
vote
0 answers

After running the GStreamer rtsp client program for a long time, free command's buff/cache increased a lot

I wrote a rtsp client program using gstreamer. After running the program for a day, free command's buff/cache increased a lot. Initially, this value was about 600, which was about 4000. Why has it increased and is not released automatically? $…
webnautes
  • 13
  • 3
1
vote
1 answer

valgrind error m_execontext.c:411 (record_ExeContext_wrk2) on jetson nano

I am trying to trace memory consumption on my nvidia jetson nano with valgrind but I get: stiv@nano:~/jsoft/dgpu_core$ valgrind --tool=massif ./build/dgpu_core ==8379== Massif, a heap profiler ==8379== Copyright (C) 2003-2017, and GNU GPL'd, by…
Stepan Yakovenko
  • 8,670
  • 28
  • 113
  • 206
1
vote
0 answers

Rotation using GStreamer/OpenCV without major latency increase (Jetson Nano, OpenCV 4.1, GStreamer 1.0, Python)

I am currently running a program in Python to display video from a RPi Camera Module V2 on the Jetson Nano. I am using OpenCV4.1 and GStreamer 1.0. I understand that rotating the image can be done with both gstreamer and opencv, as done…
cadend9
  • 97
  • 4
1
vote
1 answer

Failed to parse ONNX model to TensorRT

I'm using a jetson nano I tried to convert the onnx model https://github.com/onnx/models/tree/master/vision/body_analysis/emotion_ferplus Ran into this…
neer2005
  • 54
  • 4
1
vote
0 answers

Building pytorch on the NVIDIA Jetson Nano developer kit

I'm working on a Jetson Nano, and trying to install pytorch 1.4.0 onto it to run some toy experiments. However, I'm running into a lot of trouble with this. After failing to leverage the prebuilt wheels, I've gone the way of building from scratch,…
cbao
  • 11
  • 1
1
vote
0 answers

Getting CUDNN_STATUS_EXECUTION_FAILED error on Jetson Nano with OpenCV dnn module

I was following one of the online tutorials but I was getting this error: Traceback (most recent call last): File “ssd_object_detection.py”, line 20, in detections = net.forward() cv2.error: OpenCV(4.3.0)…
Miracle
  • 49
  • 11
1
vote
0 answers

NVIDIA Jetson Nano with Realsense 435i via Isaac - Camera not found

I posted about this over on the Isaac forums, but listing it here for visibility as well. I am trying to get the Isaac Realsense examples working on a Jetson Nano with my 435i (firmware downgraded to 5.11.15 per the Isaac documentation), but I've…
Chain_Reaktion
  • 63
  • 4
1
vote
1 answer

Run Nvidia-docker on Jetson nano and jetson xavier for deep learning framework like tensorflow

I am currently trying to run Nvidia-docker on Jetson Xavier and jetson nano with the Tensorflow framework enabled inside. but the problem I’m facing right now is related to “libcublas.so”. What I had tried the solution mentioned…
Hiren Namera
  • 390
  • 1
  • 10
1
vote
1 answer

Include OpenCV directory in YOLOv3 darknet (AlexeyAB) installation in cmake

I am trying to link OpenCV to the darknet directory. I am working with a Nvidia Jetson AGX Xavier (Ubuntu 18.04). Until recently OpenCV was installed by JetPack in the directory /usr. With this configuration the real time detection of darknet…
codetermination
  • 23
  • 4
1
vote
1 answer

Load and run test a .trt model

I need to run my model in NVIDIA JETSON T2, So I converted my working yoloV3 model into tensorRT(.trt format)(https://towardsdatascience.com/have-you-optimized-your-deep-learning-model-before-deployment-cdc3aa7f413d)This link mentioned helped me to…
Sai Krishnadas
  • 2,863
  • 9
  • 36
  • 69
1
vote
0 answers

Running yolov3 demo using jetson nano and rpi camera

I am using nvidia jetson nano with rpi camera to run yolov3, i'm 100% sure that the camera is compatible and working perfectly. when I tried to run live demo using this command ./darknet detector demo data/yolo.data cfg/yolov3_custom_train.cfg …
Mr. Jetson
  • 11
  • 1
1
vote
0 answers

Jetson Nano: Gstreamer inside docker container

I've managed to install and use docker with CUDA access on the Nvidia Jetson Nano device. The device is running a custom Yocto/poky-zeus (JetPack 4.3 supported) build . The docker image that I am testing with is an official nvidia-l4t-base image for…
Varyag
  • 676
  • 12
  • 29
1 2 3
…
26 27