[x1, y1, x2, y2] to coco format [x1, y1, w, h]

Author: ersheng-ai

README.md

@@ -40,7 +40,7 @@ A minimal PyTorch implementation of YOLOv4.
 
 # 0. Weights Download
 
-## 0.1 darknet
+## 0.1 darkent
 - baidu(https://pan.baidu.com/s/1dAGEW8cm-dqK14TbhhVetA     Extraction code:dm5b)
 - google(https://drive.google.com/open?id=1cewMfusmPjYWbrnuJRuKhPMwRe_b9PaT)
 

train.py

@@ -494,7 +494,7 @@ def evaluate(model, data_loader, cfg, device, logger=None, **kwargs):
             img_height, img_width = img.shape[:2]
             # boxes = output[...,:4].copy()  # output boxes in yolo format
             boxes = boxes.squeeze(2).cpu().detach().numpy()
-            boxes[...,:2] = boxes[...,:2] - boxes[...,2:]/2  # to coco format
+            boxes[...,2:] = boxes[...,2:] - boxes[...,:2] # Transform [x1, y1, x2, y2] to [x1, y1, w, h]
             boxes[...,0] = boxes[...,0]*img_width
             boxes[...,1] = boxes[...,1]*img_height
             boxes[...,2] = boxes[...,2]*img_width