Linaom1214/TensorRT-For-YOLO-Series
A TensorRT inference toolkit providing Python and C++ implementations for optimizing and serving various YOLO object detection models.
Velocity · 7d
+0.7
★ / day
Trend
→steady
star history
This repository provides tools to export YOLO models to ONNX format and convert them to TensorRT engine files for optimized inference. It supports YOLOv3 through YOLOv12 and includes an end-to-end mode with NMS (Non-Maximum Suppression) plugin support for production deployment. The project offers both Python and C++ inference implementations, with optional FP32/FP16/INT8 quantization support.