Update val `max_dets=args.max_det=300` (#3051)

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

ultralytics/yolo/v8/detect/val.py

@@ -223,7 +223,7 @@ class DetectionValidator(BaseValidator):
     def plot_predictions(self, batch, preds, ni):
         """Plots predicted bounding boxes on input images and saves the result."""
         plot_images(batch['img'],
-                    *output_to_target(preds, max_det=15),
+                    *output_to_target(preds, max_det=self.args.max_det),
                     paths=batch['im_file'],
                     fname=self.save_dir / f'val_batch{ni}_pred.jpg',
                     names=self.names,

ultralytics/yolo/v8/pose/val.py

@@ -156,7 +156,7 @@ class PoseValidator(DetectionValidator):
         """Plots predictions for YOLO model."""
         pred_kpts = torch.cat([p[:, 6:].view(-1, *self.kpt_shape)[:15] for p in preds], 0)
         plot_images(batch['img'],
-                    *output_to_target(preds, max_det=15),
+                    *output_to_target(preds, max_det=self.args.max_det),
                     kpts=pred_kpts,
                     paths=batch['im_file'],
                     fname=self.save_dir / f'val_batch{ni}_pred.jpg',

ultralytics/yolo/v8/segment/val.py

@@ -179,13 +179,14 @@ class SegmentationValidator(DetectionValidator):
 
     def plot_predictions(self, batch, preds, ni):
         """Plots batch predictions with masks and bounding boxes."""
-        plot_images(batch['img'],
+        plot_images(
-                    *output_to_target(preds[0], max_det=15),
+            batch['img'],
-                    torch.cat(self.plot_masks, dim=0) if len(self.plot_masks) else self.plot_masks,
+            *output_to_target(preds[0], max_det=15),  # not set to self.args.max_det due to slow plotting speed
-                    paths=batch['im_file'],
+            torch.cat(self.plot_masks, dim=0) if len(self.plot_masks) else self.plot_masks,
-                    fname=self.save_dir / f'val_batch{ni}_pred.jpg',
+            paths=batch['im_file'],
-                    names=self.names,
+            fname=self.save_dir / f'val_batch{ni}_pred.jpg',
-                    on_plot=self.on_plot)  # pred
+            names=self.names,
+            on_plot=self.on_plot)  # pred
         self.plot_masks.clear()
 
     def pred_to_json(self, predn, filename, pred_masks):