New val.py `cuda` variable (#6957)

* New val.py `cuda` variable

Fix for ONNX GPU val.

* Update val.py

val.py

             batch_size = model.batch_size
         else:
             device = model.device
-            if not pt or jit:
+            if not (pt or jit):
                 batch_size = 1  # export.py models default to batch-size 1
                 LOGGER.info(f'Forcing --batch-size 1 square inference (1,3,{imgsz},{imgsz}) for non-PyTorch models')
 
 
     # Configure
     model.eval()
+    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
     pbar = tqdm(dataloader, desc=s, bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}')  # progress bar
     for batch_i, (im, targets, paths, shapes) in enumerate(pbar):
         t1 = time_sync()
-        if pt or jit or engine:
+        if cuda:
             im = im.to(device, non_blocking=True)
             targets = targets.to(device)
         im = im.half() if half else im.float()  # uint8 to fp16/32