README.en.md

English | 简体中文

🚀 TensorRT YOLO

TensorRT-YOLO is an inference acceleration project that supports YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv9, PP-YOLOE, and PP-YOLOE+ using NVIDIA TensorRT for optimization. The project integrates EfficientNMS TensorRT plugin for enhanced post-processing and utilizes CUDA kernel functions to accelerate the preprocessing phase. TensorRT-YOLO provides support for both C++ and Python inference, aiming to deliver a fast and optimized object detection solution.

✨ Key Features

• Support for YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv9, PP-YOLOE, and PP-YOLOE+
• Support for ONNX static and dynamic export, as well as TensorRT inference
• Integration of EfficientNMS TensorRT plugin for accelerated post-processing
• Utilization of CUDA kernel functions for accelerated preprocessing
• Support for inference in both C++ and Python
• Command-line interface for quick export and inference
• One-click Docker deployment

🛠️ Requirements

• Recommended CUDA version >= 11.6
• Recommended TensorRT version >= 8.6

📦 Usage Guide

• Quick Compile and Install

• Export Models using CLI

• PTQ INT8 Quantization

• Model Inference Examples

📺 BiliBili

• 啪的一下，很快啊！TensorRT YOLOv5s 在FP16模式下，批量大小4，仅需13毫秒！

• 【TensorRT-YOLO】YOLOv9 TensorRT 推理➕EfficientNMS

• 【TensorRT-YOLO】YOLOv8 推理最速传说 1ms

📄 License

TensorRT-YOLO is licensed under the GPL-3.0 License, an OSI-approved open-source license that is ideal for students and enthusiasts, fostering open collaboration and knowledge sharing. Please refer to the LICENSE file for more details.

Thank you for choosing TensorRT-YOLO; we encourage open collaboration and knowledge sharing, and we hope you comply with the relevant provisions of the open-source license.

📞 Contact

For bug reports and feature requests regarding TensorRT-YOLO, please visit GitHub Issues!