YOLOv7

In the above figure, we can see that at 13 (ms) YOLOv7 gives approximately 55AP while YOLOv5 (r6.1) shows the same AP at approximately 27 (ms), which makes YOLOv7 120% faster than YOLOv5 (r6.1) on V100 GPU with a batch size of 1. In addition, from the figure, we can see that it has a higher AP than all the state of art detectors shown in the figure.

To learn more about the architecture behind the YOLOv7, click here.

Performance

Citation

@article{wang2022yolov7,

  title={{YOLOv7}: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors},

  author={Wang, Chien-Yao and Bochkovskiy, Alexey and Liao, Hong-Yuan Mark},

  journal={arXiv preprint arXiv:2207.02696},

  year={2022}

}