From ProventusNova DeveloperWiki
(Created page with "=How to run NVIDIA NanoOWL tutorial= ''Keywords'': ''NVIDIA Jetson, NanoOWL, object detection'' ==Description== This wiki pages shows how to run the tree prediction with a live camera tutorial from NVIDIA NanoOWL. NanoOWL is a project that optimizes OWL-ViT to run '''real-time''' on NVIDIA Jetson Orin Platforms with NVIDIA TensorRT. NanoOWL also introduces a new "tree detection" pipeline that combines OWL-ViT and CLIP to enable nested detection and classification of anyt...")
 
Line 6: Line 6:
==Set up==
==Set up==
* One of the following Jetson:
* One of the following Jetson:
⚫
** Jetson Orin NX (16 GB)
** HOla
** Jetson Orin Nano (8 GB)
** DOS
** Jetson AGX Orin (32 GB or 64 GB)


* Running one of the following JetPack versions:
⚫
* Jetson Orin NX SoM
** Jetpack 5 (L4T r35.x)
* CTI Boson NGX007 carrier board
** Jetpack 6 (L4T r36.x)
* USB Cable for flashing
* Two FRAMOS IMX464 cameras
* Keyboard
* Mouse
* Monitor

Revision as of 17:27, 26 November 2025

How to run NVIDIA NanoOWL tutorial

Keywords: NVIDIA Jetson, NanoOWL, object detection

Description

This wiki pages shows how to run the tree prediction with a live camera tutorial from NVIDIA NanoOWL. NanoOWL is a project that optimizes OWL-ViT to run real-time on NVIDIA Jetson Orin Platforms with NVIDIA TensorRT. NanoOWL also introduces a new "tree detection" pipeline that combines OWL-ViT and CLIP to enable nested detection and classification of anything, at any level, simply by providing text.

Set up

  • One of the following Jetson:
    • Jetson Orin NX (16 GB)
    • Jetson Orin Nano (8 GB)
    • Jetson AGX Orin (32 GB or 64 GB)
  • Running one of the following JetPack versions:
    • Jetpack 5 (L4T r35.x)
    • Jetpack 6 (L4T r36.x)
Retrieved from "https://developerwiki.proventusnova.com/index.php?title=How_to_run_NVIDIA_NanoOWL_tutorial&oldid=492"