modify the evaluate function in train.py along with the modification of the model inference output

Author: wenh06

train.py

@@ -487,18 +487,21 @@ def evaluate(model, data_loader, cfg, device, logger=None, **kwargs):
         # outputs = [{k: v.to(cpu_device) for k, v in t.items()} for t in outputs]
         model_time = time.time() - model_time
 
-        outputs = outputs.cpu().detach().numpy()
+        # outputs = outputs.cpu().detach().numpy()
         res = {}
-        for img, target, output in zip(images, targets, outputs):
+        # for img, target, output in zip(images, targets, outputs):
+        for img, target, (boxes, confs) in zip(images, targets, outputs):
             img_height, img_width = img.shape[:2]
-            boxes = output[...,:4].copy()  # output boxes in yolo format
+            # boxes = output[...,:4].copy()  # output boxes in yolo format
+            boxes = boxes.cpu().detach().numpy()
             boxes[...,:2] = boxes[...,:2] - boxes[...,2:]/2  # to coco format
             boxes[...,0] = boxes[...,0]*img_width
             boxes[...,1] = boxes[...,1]*img_height
             boxes[...,2] = boxes[...,2]*img_width
             boxes[...,3] = boxes[...,3]*img_height
             boxes = torch.as_tensor(boxes, dtype=torch.float32)
-            confs = output[...,4:].copy()
+            # confs = output[...,4:].copy()
+            confs = confs.cpu().detach().numpy()
             labels = np.argmax(confs, axis=1).flatten()
             labels = torch.as_tensor(labels, dtype=torch.int64)
             scores = np.max(confs, axis=1).flatten()