Scaled-YOLOv4: Scaling Cross Stage Partial Network

Scaled-YOLOv4: Scaling Cross Stage Partial Network

We show that the YOLOv4 object detection neural network based on the CSP approach, scales both up and down and is applicable to small and large networks while maintaining optimal speed and accuracy. We propose a network scaling approach that modifies not only the depth, width, resolution, but also structure of the network.YOLOv4-large model achieves state-of-the-art results: 55.4% AP (73.3% AP50) for the MS COCO dataset at a speed of 15 FPS on Tesla V100, while with the test time augmentation, YOLOv4-large achieves 55.8% AP (73.2 AP50). To the best of our knowledge, this is currently the highest accuracy on the COCO dataset among any published work. The YOLOv4-tiny model achieves 22.0% AP (42.0% AP50) at a speed of 443 FPS on RTX 2080Ti, while by using TensorRT, batch size = 4 and FP16-precision the YOLOv4-tiny achieves 1774 FPS.

Scaled-YOLOv4：扩展跨阶段局部网络

我们展示了基于CSP方法的YOLOv4对象检测神经网络，可以向上和向下缩放，并且适用于小型和大型网络，同时保持最佳速度和准确性。我们提出了一种网络缩放方法，该方法不仅可以修改深度，宽度，分辨率，还可以修改网络的结构。.. YOLOv4-large模型达到了最先进的结果：在Tesla V100上以15 FPS的速度，MS COCO数据集的AP为55.4％（AP50为73.3％），而随着测试时间的增加，YOLOv4-large的模型达到了55.8％ AP（73.2 AP50）。据我们所知，这是目前所有已发表作品中COCO数据集的最高准确性。YOLOv4-tiny模型在RTX 2080Ti上以443 FPS的速度实现了22.0％的AP（42.0％AP50），而使用TensorRT，批处理大小= 4和FP16精度，YOLOv4-tiny的模型实现了1774 FPS。 （阅读更多）