Scaled-YOLOv4: Scaling Cross Stage Partial Network
share
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 V100, while with the test time augmentation, YOLOv4-large achieves 55.8 (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 using TensorRT, batch size = 4 and FP16-precision the YOLOv4-tiny achieves 1774 FPS.
READ FULL TEXT
