ultralytics 8.0.188 fix .grad attribute leaf Tensor Warning (#5094)

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

ultralytics/nn/autobackend.py

@@ -39,6 +39,7 @@ def check_class_names(names):
 
 class AutoBackend(nn.Module):
 
+    @torch.no_grad()
     def __init__(self,
                  weights='yolov8n.pt',
                  device=torch.device('cpu'),
@@ -309,6 +310,11 @@ class AutoBackend(nn.Module):
             names = self._apply_default_class_names(data)
         names = check_class_names(names)
 
+        # Disable gradients
+        if pt:
+            for p in model.parameters():
+                p.requires_grad = False
+
         self.__dict__.update(locals())  # assign all variables to self
 
     def forward(self, im, augment=False, visualize=False):