search

WongKinYiu / PyTorch_YOLOv4

PyTorch implementation of YOLOv4
1.86k stars 585 forks source link

Why does yolov4-csp work better here than Scaled-YOLOv4 #401

Open Joker9194 opened 2 years ago

Joker9194 commented 2 years ago

Show as the ScaledYOLOv4, the coco val is

 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.67002
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.52739
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.33082
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.54036
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.62107
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.37197
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.61211
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.66544
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.49676
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.72018
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.80528

But in here, the AP is achieve 50.8%