LSH9832/yolov8_trt

A quick TensorRT deoloyment solution for YOLOv8.

40
/ 100
Emerging

This tool helps engineers quickly deploy YOLOv8 object detection models, or other ONNX-based detection models, into high-performance environments. It takes a trained model file and converts it into a TensorRT-optimized engine. The result is a highly efficient model ready for real-time object detection in applications like surveillance, robotics, or quality control.

No commits in the last 6 months.

Use this if you need to dramatically speed up the inference time of your YOLOv8 or other ONNX object detection models on NVIDIA GPUs.

Not ideal if you are still in the model training and experimentation phase, or if your deployment environment does not utilize NVIDIA GPUs and TensorRT.

real-time object detection edge AI deployment computer vision engineering model optimization industrial automation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

38

Forks

10

Language

Python

License

Apache-2.0

Last pushed

Dec 07, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LSH9832/yolov8_trt"

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