ultralytics 8.0.56 PyTorch 2.0 support and minor fixes (#1538)

Co-authored-by: N-Friederich <127681326+N-Friederich@users.noreply.github.com>
Co-authored-by: Uhrendoktor <36703334+Uhrendoktor@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Laughing <61612323+Laughing-q@users.noreply.github.com>
Co-authored-by: Aman Agarwal <amanag.11@gmail.com>
Co-authored-by: ExtReMLapin <3909752+ExtReMLapin@users.noreply.github.com>
Co-authored-by: Nadav Eidelstein <30617226+nodeav@users.noreply.github.com>

ultralytics/yolo/v8/detect/train.py

@@ -134,6 +134,7 @@ class Loss:
         else:
             i = targets[:, 0]  # image index
             _, counts = i.unique(return_counts=True)
+            counts = counts.to(dtype=torch.int32)
             out = torch.zeros(batch_size, counts.max(), 5, device=self.device)
             for j in range(batch_size):
                 matches = i == j