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
28
votes
4 answers

Cannot run tflite model on GPU (Jetson Nano) using Python

I have a quantized tflite model that I'd like to benchmark for inference on a Nvidia Jetson Nano. I use tf.lite.Interpreter() method for inference. The process doesn't seem to run on the GPU as the inference times on both CPU and GPU are the…
nithinsubbiah
  • 390
  • 3
  • 7
9
votes
2 answers

How to find the JetPack version of NVIDIA Jetson Device?

Is there a way to find the version of the currently installed JetPack on my NVIDIA Jetson Xavier AGX kit?
Pe Dro
  • 2,651
  • 3
  • 24
  • 44
8
votes
2 answers

minicom throwing an error minicom: cannot open /dev/modem: No such file or directory

I have tried to connect my Jetson Nano with TTL UART cable using minicom. When I typed sudo minicom It showed an error minicom throwing an error minicom: cannot open /dev/modem: No such file or directory
Shaik Ahmad
  • 449
  • 1
  • 3
  • 11
7
votes
3 answers

X11 forwarding requested but DISPLAY not set

I want to enable x11 forwarding on macOS connected to a Jetson Xavier nx. However, upon connecting: sudo ssh -Xvvv id@host The connection establishes successfully. But in the verbose logs, I'm getting the following: debug3: send packet: type…
zendevil
  • 899
  • 4
  • 13
  • 26
7
votes
1 answer

TF-TRT vs UFF-TensorRT

I found that we can optimize the Tensorflow model in several ways. If I am mistaken, please tell me. 1- Using TF-TRT, This API developer by tensorflow and integreted TensoRT to Tensorflow and this API called as : from…
DeeeepNet
  • 347
  • 3
  • 11
6
votes
2 answers

Jetson NX optimize tensorflow model using TensorRT

I am trying to speed up the segmentation model(unet-mobilenet-512x512). I converted my tensorflow model to tensorRT with FP16 precision mode. And the speed is lower than I expected. Before the optimization i had 7FPS on inference with .pb frozen…
Pavlo Sharhan
  • 174
  • 2
  • 10
5
votes
0 answers

Problem recording camera stream through ffmpeg - Inappropriate ioctl for device

I'm trying to record a camera stream through ffmpeg, but I'm struggling to understand how to write a correct recording command. This is the camera format according to v4l2 $ v4l2-ctl -d 1 --list-formats-ext ioctl: VIDIOC_ENUM_FMT Index :…
Otter_warrior
  • 193
  • 1
  • 12
5
votes
0 answers

How can I reduce the amount of (non-GPU) RAM overhead that PyTorch uses when using CUDA?

I'm trying to run some PyTorch models on my Jetson Nano (4GB RAM), but I've learned that PyTorch uses about 2GB of RAM just to initialize anything CUDA related. I've done some testing (with the help of this GitHub issue), and got the following…
A_toaster
  • 1,196
  • 3
  • 22
  • 50
5
votes
2 answers

What is NCHW Format?

Can someone explain to me what is NHCW format? I am working with the Jenson Inference library and for object detection the first step is called "Pre-Process" and it converts the image to NCHW format, but I don't know what this format is.
Esteban Gamez
  • 61
  • 1
  • 2
4
votes
1 answer

How to reduce Gstreamer Latency?

I wrote a pipeline that grabs a 720 X 576 image from a 1920 X 576 sensor with the v4l2src element on a Nvidia jetson xavier nx. The pipeline grabs the frame and then does 2 things: pushes the frame to the appsink element encode it and stream with…
Nir Rafman
  • 41
  • 3
4
votes
1 answer

Onnx to trt - [8] Assertion failed: creator && "Plugin not found

I am using TensorRT in order to convert a model from onnx to trt -format. The model is originally a tensorflow model from Tensorflow Model Zoo (SSD ResNet50). When I try to convert it I get the error: [E] [TRT]…
Araw
  • 2,410
  • 3
  • 29
  • 57
4
votes
0 answers

rtpjitterbuffer in gstreamer pipelines

I'm currently tuning a pair of gstreamer pipelines involving a Jetson TX2 sending and receiving audio and video. I'm trying to track down what's causing graphics artifacts on the stream coming from the TX2 where a camera streaming h264 (natively…
colmekik
  • 41
  • 2
4
votes
2 answers

OSError: libcurand.so.10: cannot open shared object file: No such file or directory

I am working on Nvidia Jetson Tx2 (with JETPACK 4.2) and installed the pytorch following this link. When I am importing torch in python its giving me an error OSError: libcurand.so.10: cannot open shared object file: No such file or directory I have…
Eren SADIKOĞLU
  • 49
  • 1
  • 1
  • 2
4
votes
1 answer

Nvidia Jetson Tx1 against jetson NANO (Benchmarking)

I am currently trying to benchmark the Jetson TX1 against the jetson NANO, according to https://elinux.org/Jetson, they both have the maxwell architecture with 128 cuda cores for NANO and 256 for TX1. This means that normally Jetson NANO will…
roody
  • 41
  • 1
4
votes
1 answer

How to use OpenCV in Numba on Jetson Xavier?

I'm trying to use OpenCV in some function which I annotate with some Numba decorators (e.g. nopython=True, parallel=True). I run this on Jetson Xavier which was flashed with Nvidia SDK Manager. Code is this: @jit(nopython=True, cache=True,…
Antonio Jurić
  • 541
  • 4
  • 15
1
2 3
…
26 27