noahmr/yolov5-tensorrt

Real-time object detection with YOLOv5 and TensorRT

46
/ 100
Emerging

This library enables real-time object detection using YOLOv5 models, converting them into a format that runs exceptionally fast on NVIDIA GPUs. It takes an existing YOLOv5 object detection model and an image or video stream, then outputs the same image or video with detected objects clearly marked. This tool is for developers building high-performance computer vision applications, especially those deploying on NVIDIA hardware like Jetson devices or Linux systems.

131 stars. No commits in the last 6 months.

Use this if you are a developer who needs to implement extremely fast, real-time object detection in C++ or Python for your applications.

Not ideal if you are looking for a no-code solution or do not have experience with C++, Python, or NVIDIA's TensorRT and CUDA development environment.

real-time-computer-vision robotics embedded-ai high-performance-computing gpu-acceleration
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

131

Forks

26

Language

C++

License

MIT

Last pushed

Feb 01, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/noahmr/yolov5-tensorrt"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.