Execute remotely on Jetson

Robotics & Edge Computing Jetson Systems Jetson Nano
1

Dear all,

I am very new in this field, so I decided to ask a possibly easy question, which I don’t know how to solve.

I would like to send an image to a Jetson Nano from my PC (Windows or Linux) to perform Some image processing and get the results (image file + txt file) back to the PC, using Python or C.

I would appreciate very much any advice on which is the best way to do it (in a programmatic way, using Python, C…)

The Jetson nano can be connected wirelessly (WiFi) or using Ethernet with cable to my home gateway, where My PC is also connected.

5

Hi,
Please provide more information about Some image processing. Do you implement CUDA code? Or you need deep learning inference?

A quick way is to use gstreamer. You may check user guide first.
https://developer.nvidia.com/embedded/dlc/l4t-accelerated-gstreamer-guide-32-2

6

Dear DaneLL,

thank you very much for your reply.

I am developing a CNN using keras+tensorflow and I would like to use the Jetson Nano to do the inference.

  • I will take a look at the gstreamer

Best regards,

  Vicenç Parisi
7

Hi,
We have DeepStream SDK for running deep learning inference. ResNet and YoloV2(V3) are demonstrated as samples. Please install through SDKManager and try.
The latest is DS4.0.2.
https://forums.developer.nvidia.com/t/announcing-deepstream-sdk-4-0-2/109325

8

Thank you again,

 I'll try it in a few days.

Vicenç Parisi


DaneLLL Jetson Partners
April 14
Hi,
We have DeepStream SDK for running deep learning inference. ResNet and YoloV2(V3) are demonstrated as samples. Please install through SDKManager and try.
The latest is DS4.0.2.

10

Dear DaneLLL,

 thank you again for your help.

Do you know if there is any implementation of Retinanet on Jetson Nano?

Best regards,

Vicenç Parisi


DaneLLL Jetson Partners
April 14
Hi,
We have DeepStream SDK for running deep learning inference. ResNet and YoloV2(V3) are demonstrated as samples. Please install through SDKManager and try.
The latest is DS4.0.2.

11

Hi,

We have a retinanet sample on our GitHub:

Thanks.