dusty-nv/jetson-inference

What It Solves

Need for accessible vision inference tools on NVIDIA Jetson platforms for UAV-based AI tasks.

Primary use cases

• Edge AI vision inference on NVIDIA Jetson platforms
• UAV onboard AI applications requiring detection/classification/segmentation
• TensorRT‑optimized inference prototyping

Secondary use cases

• General computer vision learning and experimentation
• Benchmarking Jetson inference performance
• Educational demos for deep learning on embedded

When to Use

Consider when

• Target hardware is NVIDIA Jetson (TX2, Nano, Xavier, Orin)
• Project can use MIT‑licensed software
• Active community maintenance is acceptable

Verify before adopting

• ? Confirm Jetson model compatibility with the toolkit
• ? Ensure required CUDA, cuDNN and TensorRT versions are installed
• ? Check that your models are in a supported format (e.g., Caffe) or can be converted

Where It Fits

Stack layer edge_ai

Start Here

Adoption Checklist

• Needs verification Confirm Jetson model compatibility with the toolkit
• Needs verification Ensure required CUDA, cuDNN and TensorRT versions are installed
• Needs verification Check that your models are in a supported format (e.g., Caffe) or can be converted

Each check stays "needs verification" until an official source confirms it; unconfirmed items are never marked verified.

Known Limitations & Unknowns

Known limitations

• Limited to NVIDIA Jetson hardware platforms
• Relies on TensorRT and CUDA dependencies
• Primary focus on sample applications; production‑grade integration may require additional work

Alternatives & Related Tools

Related tools

• tensorrt — Integrates with

How is it used?

Start from the recorded entry points below, then validate against the technical checklist.

• Official site https://developer.nvidia.com/embedded/twodaystoademo
• Repository https://github.com/dusty-nv/jetson-inference
• Documentation https://developer.nvidia.com/embedded/twodaystoademo

Technical checklist

• OK License identified Recorded: MIT
• OK Maintenance signal Active
• OK Verification status Official confirmed
• OK Source evidence attached 1 source record(s)
• NEEDS REVIEW Latest version recorded Not recorded

Official Links

Metadata & Governance

Dataset facts

Facts above come from the official dataset card only; unconfirmed fields stay unknown.

Related Resources & Dependencies

• tensorrt — integrates with (confirmed)

Recent Activity

Related Knowledge

Guides

• Deploying AI Inference on UAV Edge Compute — A repeatable workflow for choosing and validating an inference runtime for an onboard UAV computer.

Collections

• Edge AI Perception Starter — A starting stack for prototyping aerial perception models before edge deployment work.