https://github.com/WongKinYiu/yolov7
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
https://github.com/WongKinYiu/yolov7
darknet pytorch scaled-yolov4 yolor yolov3 yolov4 yolov7
Last synced: 26 days ago
JSON representation
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
- Host: GitHub
- URL: https://github.com/WongKinYiu/yolov7
- Owner: WongKinYiu
- License: gpl-3.0
- Created: 2022-07-06T15:14:06.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2024-08-19T12:57:04.000Z (8 months ago)
- Last Synced: 2024-10-14T08:43:05.306Z (6 months ago)
- Topics: darknet, pytorch, scaled-yolov4, yolor, yolov3, yolov4, yolov7
- Language: Jupyter Notebook
- Homepage:
- Size: 72.5 MB
- Stars: 13,294
- Watchers: 111
- Forks: 4,194
- Open Issues: 1,536
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
- awesome - WongKinYiu/yolov7 - Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors (Jupyter Notebook)
- awesome-yolo-object-detection - YOLOv7 - of-freebies sets new state-of-the-art for real-time object detectors". (**[CVPR 2023](https://arxiv.org/abs/2207.02696)**). (Summary)
- StarryDivineSky - WongKinYiu/yolov7 - of-the-art水平。该项目基于论文"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors"。YOLOv7使用了“可训练的免费技巧包”（Trainable bag-of-freebies），这意味着它可以在不增加推理成本的情况下，通过训练技巧来提高模型的性能。它在5 FPS到160 FPS的范围内，其速度和准确性都超过了所有已知的实时目标检测器。YOLOv7相比于YOLOv5，速度提高了120%，精度提高了16%。该项目提供了完整的训练和推理代码，方便用户使用和复现结果。它适用于各种实时目标检测应用场景，是一个高性能且易于使用的目标检测框架。 (对象检测_分割 / 资源传输下载)
- awesome-yolo - **Yolov7 official** - Yao Wang at all. ['Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors'](https://arxiv.org/abs/2207.02696) YOLOv7 currently outperforms all known real-time object detectors with 30 FPS or higher on GPU V100. YOLOv7-E6 object detector (56 FPS V100, 55.9% AP), (Uncategorized / Uncategorized)