ultralytics 8.2.45__tar.gz → 8.2.47__tar.gz

{ultralytics-8.2.45/ultralytics.egg-info → ultralytics-8.2.47}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.2.45
+Version: 8.2.47
 Summary: Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author: Glenn Jocher, Ayush Chaurasia, Jing Qiu
 Maintainer: Glenn Jocher, Ayush Chaurasia, Jing Qiu
@@ -30,7 +30,7 @@ Classifier: Operating System :: Microsoft :: Windows
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy<2.0.0,>=1.23.5
+Requires-Dist: numpy<2.0.0,>=1.23.0
 Requires-Dist: matplotlib>=3.3.0
 Requires-Dist: opencv-python>=4.6.0
 Requires-Dist: pillow>=7.1.2

{ultralytics-8.2.45 → ultralytics-8.2.47}/pyproject.toml

@@ -64,7 +64,7 @@ classifiers = [
 
 # Required dependencies ------------------------------------------------------------------------------------------------
 dependencies = [
-    "numpy>=1.23.5,<2.0.0", # temporary patch for compat errors https://github.com/ultralytics/yolov5/actions/runs/9538130424/job/26286956354
+    "numpy>=1.23.0,<2.0.0", # temporary patch for compat errors https://github.com/ultralytics/yolov5/actions/runs/9538130424/job/26286956354
     "matplotlib>=3.3.0",
     "opencv-python>=4.6.0",
     "pillow>=7.1.2",

{ultralytics-8.2.45 → ultralytics-8.2.47}/tests/test_python.py

@@ -236,13 +236,14 @@ def test_results(model):
     results = YOLO(WEIGHTS_DIR / model)([SOURCE, SOURCE], imgsz=160)
     for r in results:
         r = r.cpu().numpy()
+        print(r, len(r), r.path)  # print numpy attributes
         r = r.to(device="cpu", dtype=torch.float32)
         r.save_txt(txt_file=TMP / "runs/tests/label.txt", save_conf=True)
         r.save_crop(save_dir=TMP / "runs/tests/crops/")
         r.tojson(normalize=True)
         r.plot(pil=True)
         r.plot(conf=True, boxes=True)
-        print(r, len(r), r.path)
+        print(r, len(r), r.path)  # print after methods
 
 
 def test_labels_and_crops():

{ultralytics-8.2.45 → ultralytics-8.2.47}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.2.45"
+__version__ = "8.2.47"
 
 import os
 

{ultralytics-8.2.45 → ultralytics-8.2.47}/ultralytics/cfg/default.yaml

@@ -11,7 +11,7 @@ epochs: 100 # (int) number of epochs to train for
 time: # (float, optional) number of hours to train for, overrides epochs if supplied
 patience: 100 # (int) epochs to wait for no observable improvement for early stopping of training
 batch: 16 # (int) number of images per batch (-1 for AutoBatch)
-imgsz: 640 # (int | list) input images size as int for train and val modes, or list[w,h] for predict and export modes
+imgsz: 640 # (int | list) input images size as int for train and val modes, or list[h,w] for predict and export modes
 save: True # (bool) save train checkpoints and predict results
 save_period: -1 # (int) Save checkpoint every x epochs (disabled if < 1)
 cache: False # (bool) True/ram, disk or False. Use cache for data loading

{ultralytics-8.2.45 → ultralytics-8.2.47}/ultralytics/cfg/models/v10/yolov10b.yaml

@@ -3,7 +3,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
   # [depth, width, max_channels]
   b: [0.67, 1.00, 512]
 
@@ -21,7 +21,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv8.0n head
+# YOLOv10.0n head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

{ultralytics-8.2.45 → ultralytics-8.2.47}/ultralytics/cfg/models/v10/yolov10l.yaml

@@ -3,7 +3,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
   # [depth, width, max_channels]
   l: [1.00, 1.00, 512]
 
@@ -21,7 +21,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv8.0n head
+# YOLOv10.0n head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

{ultralytics-8.2.45 → ultralytics-8.2.47}/ultralytics/cfg/models/v10/yolov10m.yaml

@@ -3,7 +3,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
   # [depth, width, max_channels]
   m: [0.67, 0.75, 768]
 
@@ -21,7 +21,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv8.0n head
+# YOLOv10.0n head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

{ultralytics-8.2.45 → ultralytics-8.2.47}/ultralytics/cfg/models/v10/yolov10n.yaml

@@ -3,7 +3,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.33, 0.25, 1024]
 
@@ -21,7 +21,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv8.0n head
+# YOLOv10.0n head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

{ultralytics-8.2.45 → ultralytics-8.2.47}/ultralytics/cfg/models/v10/yolov10s.yaml

@@ -3,7 +3,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
   # [depth, width, max_channels]
   s: [0.33, 0.50, 1024]
 
@@ -21,7 +21,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv8.0n head
+# YOLOv10.0n head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

{ultralytics-8.2.45 → ultralytics-8.2.47}/ultralytics/cfg/models/v10/yolov10x.yaml

@@ -3,7 +3,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
   # [depth, width, max_channels]
   x: [1.00, 1.25, 512]
 
@@ -21,7 +21,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv8.0n head
+# YOLOv10.0n head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

{ultralytics-8.2.45 → ultralytics-8.2.47}/ultralytics/engine/results.py

@@ -743,9 +743,10 @@ class OBB(BaseTensor):
 
         Accepts both torch and numpy boxes.
         """
-        x1 = self.xyxyxyxy[..., 0].min(1).values
-        x2 = self.xyxyxyxy[..., 0].max(1).values
-        y1 = self.xyxyxyxy[..., 1].min(1).values
-        y2 = self.xyxyxyxy[..., 1].max(1).values
-        xyxy = [x1, y1, x2, y2]
-        return np.stack(xyxy, axis=-1) if isinstance(self.data, np.ndarray) else torch.stack(xyxy, dim=-1)
+        x = self.xyxyxyxy[..., 0]
+        y = self.xyxyxyxy[..., 1]
+        return (
+            torch.stack([x.amin(1), y.amin(1), x.amax(1), y.amax(1)], -1)
+            if isinstance(x, torch.Tensor)
+            else np.stack([x.min(1), y.min(1), x.max(1), y.max(1)], -1)
+        )

{ultralytics-8.2.45 → ultralytics-8.2.47}/ultralytics/solutions/ai_gym.py

@@ -53,24 +53,29 @@ class AIGym:
 
         # Check if environment supports imshow
         self.env_check = check_imshow(warn=True)
+        self.count = list()
+        self.angle = list()
+        self.stage = list()
 
-    def start_counting(self, im0, results, frame_count):
+    def start_counting(self, im0, results):
         """
         Function used to count the gym steps.
 
         Args:
             im0 (ndarray): Current frame from the video stream.
             results (list): Pose estimation data.
-            frame_count (int): Current frame count.
         """
 
         self.im0 = im0
 
-        # Initialize count, angle, and stage lists on the first frame
-        if frame_count == 1:
-            self.count = [0] * len(results[0])
-            self.angle = [0] * len(results[0])
-            self.stage = ["-" for _ in results[0]]
+        if not len(results[0]):
+            return self.im0
+
+        if len(results[0]) > len(self.count):
+            new_human = len(results[0]) - len(self.count)
+            self.count += [0] * new_human
+            self.angle += [0] * new_human
+            self.stage += ["-"] * new_human
 
         self.keypoints = results[0].keypoints.data
         self.annotator = Annotator(im0, line_width=self.tf)

{ultralytics-8.2.45 → ultralytics-8.2.47}/ultralytics/utils/__init__.py

@@ -1026,13 +1026,10 @@ class SettingsManager(dict):
         self.save()
 
 
-def deprecation_warn(arg, new_arg, version=None):
+def deprecation_warn(arg, new_arg):
     """Issue a deprecation warning when a deprecated argument is used, suggesting an updated argument."""
-    if not version:
-        version = float(__version__[:3]) + 0.2  # deprecate after 2nd major release
     LOGGER.warning(
-        f"WARNING ⚠️ '{arg}' is deprecated and will be removed in 'ultralytics {version}' in the future. "
-        f"Please use '{new_arg}' instead."
+        f"WARNING ⚠️ '{arg}' is deprecated and will be removed in in the future. " f"Please use '{new_arg}' instead."
     )
 
 

{ultralytics-8.2.45 → ultralytics-8.2.47}/ultralytics/utils/loss.py

@@ -61,39 +61,22 @@ class FocalLoss(nn.Module):
         return loss.mean(1).sum()
 
 
-class BboxLoss(nn.Module):
-    """Criterion class for computing training losses during training."""
+class DFLoss(nn.Module):
+    """Criterion class for computing DFL losses during training."""
 
-    def __init__(self, reg_max, use_dfl=False):
-        """Initialize the BboxLoss module with regularization maximum and DFL settings."""
+    def __init__(self, reg_max=16) -> None:
+        """Initialize the DFL module."""
         super().__init__()
         self.reg_max = reg_max
-        self.use_dfl = use_dfl
-
-    def forward(self, pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask):
-        """IoU loss."""
-        weight = target_scores.sum(-1)[fg_mask].unsqueeze(-1)
-        iou = bbox_iou(pred_bboxes[fg_mask], target_bboxes[fg_mask], xywh=False, CIoU=True)
-        loss_iou = ((1.0 - iou) * weight).sum() / target_scores_sum
-
-        # DFL loss
-        if self.use_dfl:
-            target_ltrb = bbox2dist(anchor_points, target_bboxes, self.reg_max)
-            loss_dfl = self._df_loss(pred_dist[fg_mask].view(-1, self.reg_max + 1), target_ltrb[fg_mask]) * weight
-            loss_dfl = loss_dfl.sum() / target_scores_sum
-        else:
-            loss_dfl = torch.tensor(0.0).to(pred_dist.device)
 
-        return loss_iou, loss_dfl
-
-    @staticmethod
-    def _df_loss(pred_dist, target):
+    def __call__(self, pred_dist, target):
         """
         Return sum of left and right DFL losses.
 
         Distribution Focal Loss (DFL) proposed in Generalized Focal Loss
         https://ieeexplore.ieee.org/document/9792391
         """
+        target = target.clamp_(0, self.reg_max - 1 - 0.01)
         tl = target.long()  # target left
         tr = tl + 1  # target right
         wl = tr - target  # weight left
@@ -104,12 +87,37 @@ class BboxLoss(nn.Module):
         ).mean(-1, keepdim=True)
 
 
+class BboxLoss(nn.Module):
+    """Criterion class for computing training losses during training."""
+
+    def __init__(self, reg_max=16):
+        """Initialize the BboxLoss module with regularization maximum and DFL settings."""
+        super().__init__()
+        self.dfl_loss = DFLoss(reg_max) if reg_max > 1 else None
+
+    def forward(self, pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask):
+        """IoU loss."""
+        weight = target_scores.sum(-1)[fg_mask].unsqueeze(-1)
+        iou = bbox_iou(pred_bboxes[fg_mask], target_bboxes[fg_mask], xywh=False, CIoU=True)
+        loss_iou = ((1.0 - iou) * weight).sum() / target_scores_sum
+
+        # DFL loss
+        if self.dfl_loss:
+            target_ltrb = bbox2dist(anchor_points, target_bboxes, self.dfl_loss.reg_max - 1)
+            loss_dfl = self.dfl_loss(pred_dist[fg_mask].view(-1, self.dfl_loss.reg_max), target_ltrb[fg_mask]) * weight
+            loss_dfl = loss_dfl.sum() / target_scores_sum
+        else:
+            loss_dfl = torch.tensor(0.0).to(pred_dist.device)
+
+        return loss_iou, loss_dfl
+
+
 class RotatedBboxLoss(BboxLoss):
     """Criterion class for computing training losses during training."""
 
-    def __init__(self, reg_max, use_dfl=False):
+    def __init__(self, reg_max):
         """Initialize the BboxLoss module with regularization maximum and DFL settings."""
-        super().__init__(reg_max, use_dfl)
+        super().__init__(reg_max)
 
     def forward(self, pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask):
         """IoU loss."""
@@ -118,9 +126,9 @@ class RotatedBboxLoss(BboxLoss):
         loss_iou = ((1.0 - iou) * weight).sum() / target_scores_sum
 
         # DFL loss
-        if self.use_dfl:
-            target_ltrb = bbox2dist(anchor_points, xywh2xyxy(target_bboxes[..., :4]), self.reg_max)
-            loss_dfl = self._df_loss(pred_dist[fg_mask].view(-1, self.reg_max + 1), target_ltrb[fg_mask]) * weight
+        if self.dfl_loss:
+            target_ltrb = bbox2dist(anchor_points, xywh2xyxy(target_bboxes[..., :4]), self.dfl_loss.reg_max - 1)
+            loss_dfl = self.dfl_loss(pred_dist[fg_mask].view(-1, self.dfl_loss.reg_max), target_ltrb[fg_mask]) * weight
             loss_dfl = loss_dfl.sum() / target_scores_sum
         else:
             loss_dfl = torch.tensor(0.0).to(pred_dist.device)
@@ -165,18 +173,19 @@ class v8DetectionLoss:
         self.use_dfl = m.reg_max > 1
 
         self.assigner = TaskAlignedAssigner(topk=tal_topk, 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.bbox_loss = BboxLoss(m.reg_max).to(device)
         self.proj = torch.arange(m.reg_max, dtype=torch.float, device=device)
 
     def preprocess(self, targets, batch_size, scale_tensor):
         """Preprocesses the target counts and matches with the input batch size to output a tensor."""
-        if targets.shape[0] == 0:
-            out = torch.zeros(batch_size, 0, 5, device=self.device)
+        nl, ne = targets.shape
+        if nl == 0:
+            out = torch.zeros(batch_size, 0, ne - 1, device=self.device)
         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)
+            out = torch.zeros(batch_size, counts.max(), ne - 1, device=self.device)
             for j in range(batch_size):
                 matches = i == j
                 n = matches.sum()
@@ -592,7 +601,7 @@ class v8ClassificationLoss:
 
     def __call__(self, preds, batch):
         """Compute the classification loss between predictions and true labels."""
-        loss = torch.nn.functional.cross_entropy(preds, batch["cls"], reduction="mean")
+        loss = F.cross_entropy(preds, batch["cls"], reduction="mean")
         loss_items = loss.detach()
         return loss, loss_items
 
@@ -606,7 +615,7 @@ class v8OBBLoss(v8DetectionLoss):
         """
         super().__init__(model)
         self.assigner = RotatedTaskAlignedAssigner(topk=10, num_classes=self.nc, alpha=0.5, beta=6.0)
-        self.bbox_loss = RotatedBboxLoss(self.reg_max - 1, use_dfl=self.use_dfl).to(self.device)
+        self.bbox_loss = RotatedBboxLoss(self.reg_max).to(self.device)
 
     def preprocess(self, targets, batch_size, scale_tensor):
         """Preprocesses the target counts and matches with the input batch size to output a tensor."""

{ultralytics-8.2.45 → ultralytics-8.2.47/ultralytics.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.2.45
+Version: 8.2.47
 Summary: Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author: Glenn Jocher, Ayush Chaurasia, Jing Qiu
 Maintainer: Glenn Jocher, Ayush Chaurasia, Jing Qiu
@@ -30,7 +30,7 @@ Classifier: Operating System :: Microsoft :: Windows
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy<2.0.0,>=1.23.5
+Requires-Dist: numpy<2.0.0,>=1.23.0
 Requires-Dist: matplotlib>=3.3.0
 Requires-Dist: opencv-python>=4.6.0
 Requires-Dist: pillow>=7.1.2

{ultralytics-8.2.45 → ultralytics-8.2.47}/ultralytics.egg-info/requires.txt

@@ -1,4 +1,4 @@
-numpy<2.0.0,>=1.23.5
+numpy<2.0.0,>=1.23.0
 matplotlib>=3.3.0
 opencv-python>=4.6.0
 pillow>=7.1.2