ulralytics 8.0.199 *.npy image loading exception handling (#5683)

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: snyk-bot <snyk-bot@snyk.io>
Co-authored-by: Yonghye Kwon <developer.0hye@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

ultralytics/models/rtdetr/train.py

@@ -13,10 +13,12 @@ from .val import RTDETRDataset, RTDETRValidator
 
 class RTDETRTrainer(DetectionTrainer):
     """
-    A class extending the DetectionTrainer class for training based on an RT-DETR detection model.
+    Trainer class for the RT-DETR model developed by Baidu for real-time object detection. Extends the DetectionTrainer
+    class for YOLO to adapt to the specific features and architecture of RT-DETR. This model leverages Vision
+    Transformers and has capabilities like IoU-aware query selection and adaptable inference speed.
 
     Notes:
-        - F.grid_sample used in rt-detr does not support the `deterministic=True` argument.
+        - F.grid_sample used in RT-DETR does not support the `deterministic=True` argument.
         - AMP training can lead to NaN outputs and may produce errors during bipartite graph matching.
 
     Example:
@@ -30,7 +32,17 @@ class RTDETRTrainer(DetectionTrainer):
     """
 
     def get_model(self, cfg=None, weights=None, verbose=True):
-        """Return a YOLO detection model."""
+        """
+        Initialize and return an RT-DETR model for object detection tasks.
+
+        Args:
+            cfg (dict, optional): Model configuration. Defaults to None.
+            weights (str, optional): Path to pre-trained model weights. Defaults to None.
+            verbose (bool): Verbose logging if True. Defaults to True.
+
+        Returns:
+            (RTDETRDetectionModel): Initialized model.
+        """
         model = RTDETRDetectionModel(cfg, nc=self.data['nc'], verbose=verbose and RANK == -1)
         if weights:
             model.load(weights)
@@ -38,31 +50,46 @@ class RTDETRTrainer(DetectionTrainer):
 
     def build_dataset(self, img_path, mode='val', batch=None):
         """
-        Build RTDETR Dataset.
+        Build and return an RT-DETR dataset for training or validation.
 
         Args:
             img_path (str): Path to the folder containing images.
-            mode (str): `train` mode or `val` mode, users are able to customize different augmentations for each mode.
-            batch (int, optional): Size of batches, this is for `rect`. Defaults to None.
+            mode (str): Dataset mode, either 'train' or 'val'.
+            batch (int, optional): Batch size for rectangle training. Defaults to None.
+
+        Returns:
+            (RTDETRDataset): Dataset object for the specific mode.
         """
-        return RTDETRDataset(
-            img_path=img_path,
-            imgsz=self.args.imgsz,
-            batch_size=batch,
-            augment=mode == 'train',  # no augmentation
-            hyp=self.args,
-            rect=False,  # no rect
-            cache=self.args.cache or None,
-            prefix=colorstr(f'{mode}: '),
-            data=self.data)
+        return RTDETRDataset(img_path=img_path,
+                             imgsz=self.args.imgsz,
+                             batch_size=batch,
+                             augment=mode == 'train',
+                             hyp=self.args,
+                             rect=False,
+                             cache=self.args.cache or None,
+                             prefix=colorstr(f'{mode}: '),
+                             data=self.data)
 
     def get_validator(self):
-        """Returns a DetectionValidator for RTDETR model validation."""
+        """
+        Returns a DetectionValidator suitable for RT-DETR model validation.
+
+        Returns:
+            (RTDETRValidator): Validator object for model validation.
+        """
         self.loss_names = 'giou_loss', 'cls_loss', 'l1_loss'
         return RTDETRValidator(self.test_loader, save_dir=self.save_dir, args=copy(self.args))
 
     def preprocess_batch(self, batch):
-        """Preprocesses a batch of images by scaling and converting to float."""
+        """
+        Preprocess a batch of images. Scales and converts the images to float format.
+
+        Args:
+            batch (dict): Dictionary containing a batch of images, bboxes, and labels.
+
+        Returns:
+            (dict): Preprocessed batch.
+        """
         batch = super().preprocess_batch(batch)
         bs = len(batch['img'])
         batch_idx = batch['batch_idx']