diff --git a/models/common.py b/models/common.py
index 48cf55795dd4..83aecb7569d6 100644
--- a/models/common.py
+++ b/models/common.py
@@ -466,7 +466,7 @@ def warmup(self, imgsz=(1, 3, 640, 640)):
         # Warmup model by running inference once
         if self.pt or self.jit or self.onnx or self.engine:  # warmup types
             if isinstance(self.device, torch.device) and self.device.type != 'cpu':  # only warmup GPU models
-                im = torch.zeros(*imgsz).to(self.device).type(torch.half if self.fp16 else torch.float)  # input image
+                im = torch.zeros(*imgsz, dtype=torch.half if self.fp16 else torch.float, device=self.device)  # input
                 self.forward(im)  # warmup
 
     @staticmethod
diff --git a/val.py b/val.py
index 8f2119531949..2dd2aec679f9 100644
--- a/val.py
+++ b/val.py
@@ -87,7 +87,7 @@ def process_batch(detections, labels, iouv):
             matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
             # matches = matches[matches[:, 2].argsort()[::-1]]
             matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
-        matches = torch.Tensor(matches).to(iouv.device)
+        matches = torch.from_numpy(matches).to(iouv.device)
         correct[matches[:, 1].long()] = matches[:, 2:3] >= iouv
     return correct
 
@@ -155,7 +155,7 @@ def run(data,
     cuda = device.type != 'cpu'
     is_coco = isinstance(data.get('val'), str) and data['val'].endswith('coco/val2017.txt')  # COCO dataset
     nc = 1 if single_cls else int(data['nc'])  # number of classes
-    iouv = torch.linspace(0.5, 0.95, 10).to(device)  # iou vector for mAP@0.5:0.95
+    iouv = torch.linspace(0.5, 0.95, 10, device=device)  # iou vector for mAP@0.5:0.95
     niou = iouv.numel()
 
     # Dataloader
@@ -196,7 +196,7 @@ def run(data,
             loss += compute_loss([x.float() for x in train_out], targets)[1]  # box, obj, cls
 
         # NMS
-        targets[:, 2:] *= torch.Tensor([width, height, width, height]).to(device)  # to pixels
+        targets[:, 2:] *= torch.tensor((width, height, width, height), device=device)  # to pixels
         lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else []  # for autolabelling
         t3 = time_sync()
         out = non_max_suppression(out, conf_thres, iou_thres, labels=lb, multi_label=True, agnostic=single_cls)