Lcod
April 21, 2025, 12:43pm
1
Dear Ultralytics Team,
I am writing to request your guidance regarding the most appropriate Docker image for deploying YOLOv8 on a Jetson Orin Nano device.
Hardware and Software Environment
Jetson Orin Nano platform
Ubuntu 22.04.5 LTS
JetPack 6.2 (L4T 36.4.3)
Docker version 28.0.1
ARM64/AArch64 architecture
Raspberry Pi Camera Module 3 Wide (connected via CSI)
Functional Requirements
I need to implement real-time object detection using YOLOv8n with the following capabilities:
Process video input at 1080p resolution
Convert the YOLOv8n model to TensorRT engine for performance optimization
Achieve optimal inference speed on the Jetson hardware
Information Requested
Which Ultralytics Docker image would you recommend for the specified Jetson environment?
Are there specific configuration parameters that would optimize performance for this hardware and camera setup?
Do you have best practices for YOLOv8n deployment on Jetson platforms with CSI cameras?
There are Ultralytics maintained Dockerfiles. Here’s the one for JetPack 6
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Builds ultralytics/ultralytics:jetson-jetpack6 image on DockerHub https://hub.docker.com/r/ultralytics/ultralytics
# Supports JetPack6.1 for YOLO11 on Jetson AGX Orin, Orin NX and Orin Nano Series
# Start FROM https://catalog.ngc.nvidia.com/orgs/nvidia/containers/l4t-jetpack
FROM nvcr.io/nvidia/l4t-jetpack:r36.4.0
# Set environment variables
ENV PYTHONUNBUFFERED=1 \
PYTHONDONTWRITEBYTECODE=1 \
PIP_NO_CACHE_DIR=1 \
PIP_BREAK_SYSTEM_PACKAGES=1
# Downloads to user config dir
ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.ttf \
https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.Unicode.ttf \
/root/.config/Ultralytics/
# Install dependencies
This file has been truncated. show original
1 Like
Lcod
May 11, 2025, 5:36pm
3
Everything was well-explained and clearly documented on the website. My oversight was not taking the extra step to verify which system I have and which Docker image would be compatible with it—likely a junior-level mistake on my part.
Everything is now working smoothly, efficiently, and in a user-friendly manner.
Thank you for your support!
1 Like
It’s great to hear that everything is working smoothly for you now, Lcod!
We’re pleased that the documentation was helpful. The Ultralytics team and the YOLO community work hard to make the tools accessible and user-friendly.
Happy coding!