论文标题
YOLOV7：可训练的释放袋为实时对象探测器设置了新的最新最先进
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
论文作者
论文摘要
Yolov7在5 fps到160 fps的速度和精度上都超过了所有已知对象探测器，并且在所有已知的实时对象探测器中，GPU V100上的所有已知实时对象探测器的精度最高为56.8％AP。 YOLOV7-E6对象检测器（56 fps v100，55.9％AP）优于两个基于变压器的检测器SWIN-L-l-CASCADE掩膜R-CNN（9.2 fps a100，53.9％AP）的速度为509％，准确性为2％，基于基于探测器Convental contnext-contnext-xl cascade cascade cascade cascade cans r-cnn（8.6 fps r-cnn（8.6 fps r-cn）速度和0.7％AP的准确性以及Yolov7的表现均优于：Yolor，Yolox，Scaled-Yolov4，Yolov5，Yolov5，detr，Detr，可变形的DETR，DINO-5Scale-R50，VIT-ADAPTER-B和许多其他速度和准确性的其他对象探测器。此外，我们仅在不使用任何其他数据集或预先训练的权重的情况下，仅在MS Coco数据集上训练Yolov7。源代码在https://github.com/wongkinyiu/yolov7中发布。
YOLOv7 surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 160 FPS and has the highest accuracy 56.8% AP among all known real-time object detectors with 30 FPS or higher on GPU V100. YOLOv7-E6 object detector (56 FPS V100, 55.9% AP) outperforms both transformer-based detector SWIN-L Cascade-Mask R-CNN (9.2 FPS A100, 53.9% AP) by 509% in speed and 2% in accuracy, and convolutional-based detector ConvNeXt-XL Cascade-Mask R-CNN (8.6 FPS A100, 55.2% AP) by 551% in speed and 0.7% AP in accuracy, as well as YOLOv7 outperforms: YOLOR, YOLOX, Scaled-YOLOv4, YOLOv5, DETR, Deformable DETR, DINO-5scale-R50, ViT-Adapter-B and many other object detectors in speed and accuracy. Moreover, we train YOLOv7 only on MS COCO dataset from scratch without using any other datasets or pre-trained weights. Source code is released in https://github.com/WongKinYiu/yolov7.
