ultralytics 8.0.52 reduced TAL CUDA usage and AMP check fix (#1333)

Co-authored-by: CNH5 <74132034+CNH5@users.noreply.github.com>
Co-authored-by: Huijae Lee <46982469+ZeroAct@users.noreply.github.com>
Co-authored-by: Lorenzo Mammana <lorenzom96@hotmail.it>
Co-authored-by: Laughing <61612323+Laughing-q@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Hardik Dava <39372750+hardikdava@users.noreply.github.com>
Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com>

ultralytics/yolo/v8/detect/train.py

@@ -124,13 +124,8 @@ class Loss:
         self.device = device
 
         self.use_dfl = m.reg_max > 1
-        roll_out_thr = h.min_memory if h.min_memory > 1 else 64 if h.min_memory else 0  # 64 is default
 
-        self.assigner = TaskAlignedAssigner(topk=10,
-                                            num_classes=self.nc,
-                                            alpha=0.5,
-                                            beta=6.0,
-                                            roll_out_thr=roll_out_thr)
+        self.assigner = TaskAlignedAssigner(topk=10, num_classes=self.nc, alpha=0.5, beta=6.0)
         self.bbox_loss = BboxLoss(m.reg_max - 1, use_dfl=self.use_dfl).to(device)
         self.proj = torch.arange(m.reg_max, dtype=torch.float, device=device)
 

ultralytics/yolo/v8/detect/val.py

@@ -113,6 +113,7 @@ class DetectionValidator(BaseValidator):
 
     def finalize_metrics(self, *args, **kwargs):
         self.metrics.speed = self.speed
+        self.metrics.confusion_matrix = self.confusion_matrix
 
     def get_stats(self):
         stats = [torch.cat(x, 0).cpu().numpy() for x in zip(*self.stats)]  # to numpy