emptysoal/YOLOv5-TensorRT-lib-Python

The code of YOLOv5 inferencing with TensorRT C++ api is packaged into a dynamic link library , then called through Python.

38
/ 100
Emerging

This project helps computer vision engineers and AI developers quickly deploy YOLOv5 object detection models. It takes pre-trained YOLOv5 models and converts them into a highly optimized format (.plan file). This enables very fast object detection from images, making it suitable for applications requiring high-speed processing, such as real-time video analysis or embedded systems.

Use this if you need to perform extremely fast object detection using YOLOv5 models in a production environment or on resource-constrained devices, while still leveraging Python for easy integration with other systems.

Not ideal if you are primarily experimenting with model training or fine-tuning, as this tool focuses on deployment optimization rather than model development.

object-detection real-time-vision embedded-AI computer-vision model-deployment
No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

15

Forks

2

Language

Cuda

License

MIT

Last pushed

Oct 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/emptysoal/YOLOv5-TensorRT-lib-Python"

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