English | 简体中文
)
TensorRT-YOLO is an inference acceleration project that supports YOLOv3, YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv9, YOLOv10, YOLO11, PP-YOLOE and PP-YOLOE+ using NVIDIA TensorRT for optimization. The project not only integrates the TensorRT plugin to enhance post-processing effects but also utilizes CUDA kernel functions and CUDA graphs to accelerate inference. TensorRT-YOLO provides support for both C++ and Python inference, aiming to deliver a fast and optimized object detection solution.
- Support for YOLOv3, YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv9, YOLOv10, YOLO11, PP-YOLOE and PP-YOLOE+
- Support Detect and OBB Detect models
- Support for ONNX static and dynamic export, as well as TensorRT inference
- Integration of TensorRT plugin for accelerated post-processing
- Utilization of CUDA kernel functions for accelerated preprocessing
- Utilization of CUDA graphs for accelerated inference process
- Support for inference in both C++ and Python
- Command-line interface for quick export and inference
- One-click Docker deployment
- Recommended CUDA version >= 11.6
- Recommended TensorRT version >= 8.6
Open source projects require effort. If this project has been helpful to you, consider buying the author a coffee. Your support is the greatest motivation for the developer to keep maintaining the project!
It's recommended to use Alipay, as WeChat doesn't provide the avatar. Please note "TensorRT-YOLO" in the transfer.
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.
For bug reports and feature requests regarding TensorRT-YOLO, please visit GitHub Issues!