cyrusbehr/YOLOv8-TensorRT-CPP

YOLOv8 TensorRT C++ Implementation

45
/ 100
Emerging

This project helps operations engineers and robotics developers integrate advanced computer vision capabilities into their C++ applications that run on NVIDIA GPUs. It takes a pre-trained YOLOv8 object detection, segmentation, or pose estimation model and converts it into an optimized format for high-speed analysis. The output provides precise bounding boxes, segmentation masks, or keypoint detections from images or video feeds, enabling real-time decision-making.

718 stars. No commits in the last 6 months.

Use this if you need to deploy fast, accurate, real-time object detection, semantic segmentation, or body pose estimation in a C++ application running on an NVIDIA GPU.

Not ideal if you are developing in Python or do not have access to an NVIDIA GPU, as it is specifically designed for C++ and TensorRT.

real-time vision robotics industrial automation video analytics embedded vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

718

Forks

83

Language

C++

License

MIT

Last pushed

Feb 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/cyrusbehr/YOLOv8-TensorRT-CPP"

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