`ultralytics 8.0.11` bug fixes and performance improvements (#495)

Co-authored-by: Laughing <61612323+Laughing-q@users.noreply.github.com>
Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

docs/predict.md

@@ -14,7 +14,7 @@ Inference or prediction of a task returns a list of `Results` objects. Alternati
     === "Getting a Generator"
         ```python
         inputs = [img, img] # list of np arrays
-        results = model(inputs, stream="True") # Generator of Results objects
+        results = model(inputs, stream=True) # Generator of Results objects
         for result in results:
             boxes = results.boxes # Boxes object for bbox outputs
             masks = results.masks # Masks object for segmenation masks outputs

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, GPL-3.0 license
 
-__version__ = "8.0.9"
+__version__ = "8.0.11"
 
 from ultralytics.yolo.engine.model import YOLO
 from ultralytics.yolo.utils import ops

ultralytics/yolo/data/dataloaders/v5loader.py

@@ -493,7 +493,7 @@ class LoadImagesAndLabels(Dataset):
             cache, exists = np.load(cache_path, allow_pickle=True).item(), True  # load dict
             assert cache['version'] == self.cache_version  # matches current version
             assert cache['hash'] == get_hash(self.label_files + self.im_files)  # identical hash
-        except Exception:
+        except (FileNotFoundError, AssertionError):
             cache, exists = self.cache_labels(cache_path, prefix), False  # run cache ops
 
         # Display cache

ultralytics/yolo/data/dataset.py

@@ -105,7 +105,7 @@ class YOLODataset(BaseDataset):
             cache, exists = np.load(str(cache_path), allow_pickle=True).item(), True  # load dict
             assert cache["version"] == self.cache_version  # matches current version
             assert cache["hash"] == get_hash(self.label_files + self.im_files)  # identical hash
-        except Exception:
+        except (FileNotFoundError, AssertionError):
             cache, exists = self.cache_labels(cache_path), False  # run cache ops
 
         # Display cache

ultralytics/yolo/engine/results.py

@@ -95,6 +95,18 @@ class Results:
 
         return s
 
+    def __getattr__(self, attr):
+        name = self.__class__.__name__
+        raise AttributeError(f"""
+            '{name}' object has no attribute '{attr}'. Valid '{name}' object attributes and properties are:
+
+            Attributes:
+                boxes (Boxes, optional): A Boxes object containing the detection bounding boxes.
+                masks (Masks, optional): A Masks object containing the detection masks.
+                probs (torch.Tensor, optional): A tensor containing the detection class probabilities.
+                orig_shape (tuple, optional): Original image size.
+            """)
+
 
 class Boxes:
     """
@@ -200,6 +212,25 @@ class Boxes:
         boxes = self.boxes[idx]
         return Boxes(boxes, self.orig_shape)
 
+    def __getattr__(self, attr):
+        name = self.__class__.__name__
+        raise AttributeError(f"""
+            '{name}' object has no attribute '{attr}'. Valid '{name}' object attributes and properties are:
+
+            Attributes:
+                boxes (torch.Tensor) or (numpy.ndarray): A tensor or numpy array containing the detection boxes,
+                    with shape (num_boxes, 6).
+                orig_shape (torch.Tensor) or (numpy.ndarray): Original image size, in the format (height, width).
+
+            Properties:
+                xyxy (torch.Tensor) or (numpy.ndarray): The boxes in xyxy format.
+                conf (torch.Tensor) or (numpy.ndarray): The confidence values of the boxes.
+                cls (torch.Tensor) or (numpy.ndarray): The class values of the boxes.
+                xywh (torch.Tensor) or (numpy.ndarray): The boxes in xywh format.
+                xyxyn (torch.Tensor) or (numpy.ndarray): The boxes in xyxy format normalized by original image size.
+                xywhn (torch.Tensor) or (numpy.ndarray): The boxes in xywh format normalized by original image size.
+            """)
+
 
 class Masks:
     """
@@ -262,6 +293,19 @@ class Masks:
         masks = self.masks[idx]
         return Masks(masks, self.im_shape, self.orig_shape)
 
+    def __getattr__(self, attr):
+        name = self.__class__.__name__
+        raise AttributeError(f"""
+            '{name}' object has no attribute '{attr}'. Valid '{name}' object attributes and properties are:
+
+            Attributes:
+                masks (torch.Tensor): A tensor containing the detection masks, with shape (num_masks, height, width).
+                orig_shape (tuple): Original image size, in the format (height, width).
+
+            Properties:
+                segments (list): A list of segments which includes x,y,w,h,label,confidence, and mask of each detection masks.
+            """)
+
 
 if __name__ == "__main__":
     # test examples

ultralytics/yolo/utils/__init__.py

@@ -379,7 +379,7 @@ def set_sentry(dsn=None):
             release=ultralytics.__version__,
             send_default_pii=True,
             environment='production',  # 'dev' or 'production'
-            ignore_errors=[KeyboardInterrupt, torch.cuda.OutOfMemoryError])
+            ignore_errors=[KeyboardInterrupt])
 
 
 def get_settings(file=USER_CONFIG_DIR / 'settings.yaml', version='0.0.1'):

ultralytics/yolo/v8/detect/train.py

@@ -177,7 +177,7 @@ class Loss:
             anchor_points * stride_tensor, gt_labels, gt_bboxes, mask_gt)
 
         target_bboxes /= stride_tensor
-        target_scores_sum = target_scores.sum()
+        target_scores_sum = max(target_scores.sum(), 1)
 
         # cls loss
         # loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum  # VFL way

ultralytics/yolo/v8/segment/train.py

@@ -99,7 +99,7 @@ class SegLoss(Loss):
             pred_scores.detach().sigmoid(), (pred_bboxes.detach() * stride_tensor).type(gt_bboxes.dtype),
             anchor_points * stride_tensor, gt_labels, gt_bboxes, mask_gt)
 
-        target_scores_sum = target_scores.sum()
+        target_scores_sum = max(target_scores.sum(), 1)
 
         # cls loss
         # loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum  # VFL way