# yolov12 **Repository Path**: summry/yolov12 ## Basic Information - **Project Name**: yolov12 - **Description**: No description available - **Primary Language**: Python - **License**: AGPL-3.0 - **Default Branch**: main - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2025-03-06 - **Last Updated**: 2025-04-03 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README

YOLOv12

YOLOv12: Attention-Centric Real-Time Object Detectors

[Yunjie Tian](https://sunsmarterjie.github.io/)1, [Qixiang Ye](https://people.ucas.ac.cn/~qxye?language=en)2, [David Doermann](https://cse.buffalo.edu/~doermann/)1 1 University at Buffalo, SUNY, 2 University of Chinese Academy of Sciences.


Comparison with popular methods in terms of latency-accuracy (left) and FLOPs-accuracy (right) trade-offs

[![arXiv](https://img.shields.io/badge/arXiv-2502.12524-b31b1b.svg)](https://arxiv.org/abs/2502.12524) [![Hugging Face Demo](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/sunsmarterjieleaf/yolov12) Open In Colab [![Kaggle Notebook](https://img.shields.io/badge/Kaggle-Notebook-blue?logo=kaggle)](https://www.kaggle.com/code/jxxn03x/yolov12-on-custom-data) [![deploy](https://media.roboflow.com/deploy.svg)](https://blog.roboflow.com/use-yolov12-with-roboflow/#deploy-yolov12-models-with-roboflow) ## Updates - 2025/02/24: Some blog introductions: [ultralytics](https://docs.ultralytics.com/models/yolo12/), [LearnOpenCV](https://learnopencv.com/yolov12/), [Medium@Mert](https://medium.com/@Mert.A/how-to-use-yolov12-for-object-detection-a93b3c2592a3). Thanks to them! - 2025/02/22: [YOLOv12 TensorRT CPP Inference Repo + Google Colab Notebook Support](https://github.com/mohamedsamirx/YOLOv12-TensorRT-CPP). - 2025/02/22: [Android deploy](https://github.com/mpj1234/ncnn-yolov12-android/tree/main). [TensorRT-YOLO](https://github.com/laugh12321/TensorRT-YOLO) accelerates yolo12 inference. Thanks to them! - 2025/02/21: Try yolo12 for classification, oriented bounding boxes, pose estimation, and instance segmentation at [ultralytics](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/models/12). Please pay attention to this [issue](https://github.com/sunsmarterjie/yolov12/issues/29). Thanks to them! - 2025/02/20: [Any computer or edge device?](https://github.com/roboflow/inference) Support yolo12 now. - 2025/02/20: [ONNX CPP Version](https://github.com/mohamedsamirx/YOLOv12-ONNX-CPP). Train a yolov12 model on a custom dataset: [Blog](https://blog.roboflow.com/train-yolov12-model/) and [Youtube](https://www.youtube.com/watch?v=fksJmIMIfXo). [Train YOLO12 on a custom dataset step-by-step](https://youtu.be/dO8k5rgXG0M) by [Noor](https://github.com/noorkhokhar99). - 2025/02/19: [arXiv version](https://arxiv.org/abs/2502.12524) is public. [Demo](https://huggingface.co/spaces/sunsmarterjieleaf/yolov12) is available (try [Demo2](https://huggingface.co/spaces/sunsmarterjieleaf/yolov12_demo2) [Demo3](https://huggingface.co/spaces/sunsmarterjieleaf/yolov12_demo3) if busy).
Abstract Enhancing the network architecture of the YOLO framework has been crucial for a long time but has focused on CNN-based improvements despite the proven superiority of attention mechanisms in modeling capabilities. This is because attention-based models cannot match the speed of CNN-based models. This paper proposes an attention-centric YOLO framework, namely YOLOv12, that matches the speed of previous CNN-based ones while harnessing the performance benefits of attention mechanisms. YOLOv12 surpasses all popular real-time object detectors in accuracy with competitive speed. For example, YOLOv12-N achieves 40.6% mAP with an inference latency of 1.64 ms on a T4 GPU, outperforming advanced YOLOv10-N / YOLOv11-N by 2.1%/1.2% mAP with a comparable speed. This advantage extends to other model scales. YOLOv12 also surpasses end-to-end real-time detectors that improve DETR, such as RT-DETR / RT-DETRv2: YOLOv12-S beats RT-DETR-R18 / RT-DETRv2-R18 while running 42% faster, using only 36% of the computation and 45% of the parameters.
## Main Results | Model | size
(pixels) | mAPval
50-95 | Speed
T4 TensorRT10
| params
(M) | FLOPs
(G) | | :----------------------------------------------------------------------------------- | :-------------------: | :-------------------:| :------------------------------:| :-----------------:| :---------------:| | [YOLO12n](https://github.com/sunsmarterjie/yolov12/releases/download/v1.0/yolov12n.pt) | 640 | 40.6 | 1.64 | 2.6 | 6.5 | | [YOLO12s](https://github.com/sunsmarterjie/yolov12/releases/download/v1.0/yolov12s.pt) | 640 | 48.0 | 2.61 | 9.3 | 21.4 | | [YOLO12m](https://github.com/sunsmarterjie/yolov12/releases/download/v1.0/yolov12m.pt) | 640 | 52.5 | 4.86 | 20.2 | 67.5 | | [YOLO12l](https://github.com/sunsmarterjie/yolov12/releases/download/v1.0/yolov12l.pt) | 640 | 53.7 | 6.77 | 26.4 | 88.9 | | [YOLO12x](https://github.com/sunsmarterjie/yolov12/releases/download/v1.0/yolov12x.pt) | 640 | 55.2 | 11.79 | 59.1 | 199.0 | ## Installation ``` wget https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.3/flash_attn-2.7.3+cu11torch2.2cxx11abiFALSE-cp311-cp311-linux_x86_64.whl conda create -n yolov12 python=3.11 conda activate yolov12 pip install -r requirements.txt pip install -e . ``` ## Validation [`yolov12n`](https://github.com/sunsmarterjie/yolov12/releases/download/v1.0/yolov12n.pt) [`yolov12s`](https://github.com/sunsmarterjie/yolov12/releases/download/v1.0/yolov12s.pt) [`yolov12m`](https://github.com/sunsmarterjie/yolov12/releases/download/v1.0/yolov12m.pt) [`yolov12l`](https://github.com/sunsmarterjie/yolov12/releases/download/v1.0/yolov12l.pt) [`yolov12x`](https://github.com/sunsmarterjie/yolov12/releases/download/v1.0/yolov12x.pt) ```python from ultralytics import YOLO model = YOLO('yolov12{n/s/m/l/x}.pt') model.val(data='coco.yaml', save_json=True) ``` ## Training ```python from ultralytics import YOLO model = YOLO('yolov12n.yaml') # Train the model results = model.train( data='coco.yaml', epochs=600, batch=256, imgsz=640, scale=0.5, # S:0.9; M:0.9; L:0.9; X:0.9 mosaic=1.0, mixup=0.0, # S:0.05; M:0.15; L:0.15; X:0.2 copy_paste=0.1, # S:0.15; M:0.4; L:0.5; X:0.6 device="0,1,2,3", ) # Evaluate model performance on the validation set metrics = model.val() # Perform object detection on an image results = model("path/to/image.jpg") results[0].show() ``` ## Prediction ```python from ultralytics import YOLO model = YOLO('yolov12{n/s/m/l/x}.pt') model.predict() ``` ## Export ```python from ultralytics import YOLO model = YOLO('yolov12{n/s/m/l/x}.pt') model.export(format="engine", half=True) # or format="onnx" ``` ## Demo ``` python app.py # Please visit http://127.0.0.1:7860 ``` ## Acknowledgement The code is based on [ultralytics](https://github.com/ultralytics/ultralytics). Thanks for their excellent work! ## Citation ```BibTeX @article{tian2025yolov12, title={YOLOv12: Attention-Centric Real-Time Object Detectors}, author={Tian, Yunjie and Ye, Qixiang and Doermann, David}, journal={arXiv preprint arXiv:2502.12524}, year={2025} } ```