For questions specific to programming the NVIDIA "Jetson Nano" device. When using this tag also include the more generic [nvidia-jetson] tag. Please also tag the language you are coding in and the framework you are using for context.
Questions tagged [nvidia-jetson-nano]
290 questions
0
votes
1 answer
Compiling OpenCV creates cuda error - recipe for target 'modules/core/CMakeFiles/opencv_core.dir/src/opengl.cpp.o' failed
I'm trying to compile openCV but it doesn't seem to work somehow.
Is this a problem with cuda?
I am running this in a docker-container (nvidia-docker)
Hardware is a Jetson Nano with newest JetPack - Version
What could that problem be?
[ 32%]…
Antax
- 496
- 6
- 13
0
votes
1 answer
How to prioritize jetson nano swap file
We have installed Jetpack 4.2.3 on jetson nano. This has created a 2 GB built in zram memory.
We have additionally added 4 GB swap file using the following
https://www.jetsonhacks.com/2019/04/14/jetson-nano-use-more-memory/
The system is taking…
Razack
- 1,826
- 2
- 16
- 37
0
votes
1 answer
Converting TF 2.0 saved model for TensorRT on Jetson Nano
I am trying to convert a TF 2.0 saved_model to tensorRT on the Jetson Nano.
The model was saved in TF 2.0.0. The nano has Jetpack 4.2.2 w/ TensorRT __ and Tensorflow 1.14 (that is the latest Tensorflow release for Jetson).
I have been following the…
DankMasterDan
- 1,900
- 4
- 23
- 35
0
votes
0 answers
I am getting valueError: Input contains NaN, infinity or a value too large for dtype('float64'). while running on Jetson Nano
When i used knn for recognition and running following function:
def predict(X_img_path, knn_clf=None, model_path=None, distance_threshold=0.49):
if not os.path.isfile(X_img_path) or os.path.splitext(X_img_path)[1][1:] not in
…
safe pro
- 1
- 1
0
votes
1 answer
Ubuntu Mobile Broadband
I am having trouble setting up cellular connection on my Jetson Nano to T-Mobile with a Huawei E220 stick. It used to be able to connect but it does not connect any more. PIN is disabled, and stick works fine under Windows. I think it might be…
JC-
- 1,200
- 2
- 9
- 12
0
votes
1 answer
Face recognition doesn't work on Jetson Nano
I want to minimize my face recognition system from PC to a Jetson Nano board
I use this example code:
https://github.com/ageitgey/face_recognition/blob/master/examples/facerec_from_webcam_faster.py
The system works well when running on PC, it can…
Farhan Rabbaanii
- 393
- 6
- 16
0
votes
0 answers
script get killed when encoding process
i want to minimize my face recognition system from PC to Jetson nano.
after the system done encoding some images in dataset, the system freeze for a while and get killed.
this my code:
import face_recognition
import cv2
import numpy as np
import…
Farhan Rabbaanii
- 393
- 6
- 16
0
votes
0 answers
cmake install pointing to minimum python version when installing opencv
Used this to build inside release directory of opencv
To build OpenCV inside the virtual environment offersTest
cmake -D WITH_CUDA=ON -D CUDA_ARCH_BIN="5.3" -D CUDA_ARCH_PTX="" -D OPENCV_EXTRA_MODULES_PATH=../../opencv_contrib-4.0.0/modules -D…
Santhosh Dhaipule Chandrakanth
- 1,134
- 12
- 26
0
votes
1 answer
No ethernet access on jetson nano with custom yocto image
I've created a very minimal image for the jetson nano with the recepe:
inherit core-image
inherit distro_features_check
REQUIRED_DISTRO_FEATURES = "x11"
IMAGE_FEATURES += "package-management splash"
CORE_OS = "packagegroup-core-boot \
…
Varyag
- 676
- 12
- 29
0
votes
1 answer
Can i use cuda folder from meta-tegra master branch in thud meta-tegra branch?
I'm attempting to create an image for my NVIDIA jetsons-nano (following this guide).
When building the very basic image, the build terminates with an error saying it cannot find cuda-repo-l4t-10-0-local-10.0.166... and that is because the NVIDIA…
Varyag
- 676
- 12
- 29
-1
votes
0 answers
Convert pytorch trained model .pt file into a .wts plaintext file
I have a custom pretrained pytorch model and I need to convert it into a .wts file to run a library on it but I am lost as to how to accomplish this.
Details:
I used YOLOv5 to train a model and save it as a .pt file. I need to run this model on…
Ranai Srivastav
- 13
- 6
-1
votes
1 answer
ROS Docker changes are not persistent / retained upon exit
Hi all,
I spent a whole lot of time today inside a docker container, installing software and making changes to the environment, setting everything up the way I need it.
Then I realized none of that has been retained. Here is exactly what I have…
Aotearoa_DEV
- 1
- 2
-1
votes
1 answer
nvidia jetson nano vnc connection without HDMI plugged in / headless
With the standard j4t image that should be installed to the jetson nano (in this case the 4GB dev edition) the desktop is not rendered correctly. The UI shows artifacts and does not function like expected. For example the Terminal would not start at…
Pascal
- 812
- 7
- 19
-1
votes
1 answer
I can't install tensorflow on Jetson Nano
I am currently working on my Nvidia Jetson Nano 4GB following this guide. I try to install tensorflow but a few moments later I have THAT 2500lines error: 'python version don't match your environment' . Okay, I want to see my actual version and I…
-1
votes
1 answer
Flask app is keep on loading at the time of prediction(TensorRT)
This is in the continuation to the question
Facing issue while running Flask app with TensorRt model on jetson nano
Above is resolve but when I am running flask 'app' it keep loading and not showing video.
code:
def callback():
cuda.init()
…
Akshay Sharma
- 11
- 8