ultralytics 8.2.71__tar.gz → 8.2.72__tar.gz

{ultralytics-8.2.71/ultralytics.egg-info → ultralytics-8.2.72}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.2.71
+Version: 8.2.72
 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

{ultralytics-8.2.71 → ultralytics-8.2.72}/tests/test_cli.py

@@ -8,6 +8,7 @@ from PIL import Image
 from tests import CUDA_DEVICE_COUNT, CUDA_IS_AVAILABLE
 from ultralytics.cfg import TASK2DATA, TASK2MODEL, TASKS
 from ultralytics.utils import ASSETS, WEIGHTS_DIR, checks
+from ultralytics.utils.torch_utils import TORCH_1_9
 
 # Constants
 TASK_MODEL_DATA = [(task, WEIGHTS_DIR / TASK2MODEL[task], TASK2DATA[task]) for task in TASKS]
@@ -57,6 +58,8 @@ def test_rtdetr(task="detect", model="yolov8n-rtdetr.yaml", data="coco8.yaml"):
     # Warning: must use imgsz=640 (note also add coma, spaces, fraction=0.25 args to test single-image training)
     run(f"yolo train {task} model={model} data={data} --imgsz= 160 epochs =1, cache = disk fraction=0.25")
     run(f"yolo predict {task} model={model} source={ASSETS / 'bus.jpg'} imgsz=160 save save_crop save_txt")
+    if TORCH_1_9:
+        run(f"yolo predict {task} model='rtdetr-l.pt' source={ASSETS / 'bus.jpg'} imgsz=160 save save_crop save_txt")
 
 
 @pytest.mark.skipif(checks.IS_PYTHON_3_12, reason="MobileSAM with CLIP is not supported in Python 3.12")

{ultralytics-8.2.71 → ultralytics-8.2.72}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.2.71"
+__version__ = "8.2.72"
 
 import os
 

{ultralytics-8.2.71 → ultralytics-8.2.72}/ultralytics/models/sam2/predict.py

@@ -102,28 +102,23 @@ class SAM2Predictor(Predictor):
         if bboxes is not None:
             bboxes = torch.as_tensor(bboxes, dtype=torch.float32, device=self.device)
             bboxes = bboxes[None] if bboxes.ndim == 1 else bboxes
-            bboxes *= r
+            bboxes = bboxes.view(-1, 2, 2) * r
+            bbox_labels = torch.tensor([[2, 3]], dtype=torch.int32, device=bboxes.device).expand(len(bboxes), -1)
+            # NOTE: merge "boxes" and "points" into a single "points" input
+            # (where boxes are added at the beginning) to model.sam_prompt_encoder
+            if points is not None:
+                points = torch.cat([bboxes, points], dim=1)
+                labels = torch.cat([bbox_labels, labels], dim=1)
+            else:
+                points, labels = bboxes, bbox_labels
         if masks is not None:
             masks = torch.as_tensor(masks, dtype=torch.float32, device=self.device).unsqueeze(1)
 
         points = (points, labels) if points is not None else None
-        # TODO: Embed prompts
-        # if bboxes is not None:
-        #     box_coords = bboxes.reshape(-1, 2, 2)
-        #     box_labels = torch.tensor([[2, 3]], dtype=torch.int, device=bboxes.device)
-        #     box_labels = box_labels.repeat(bboxes.size(0), 1)
-        #     # we merge "boxes" and "points" into a single "concat_points" input (where
-        #     # boxes are added at the beginning) to sam_prompt_encoder
-        #     if concat_points is not None:
-        #         concat_coords = torch.cat([box_coords, concat_points[0]], dim=1)
-        #         concat_labels = torch.cat([box_labels, concat_points[1]], dim=1)
-        #         concat_points = (concat_coords, concat_labels)
-        #     else:
-        #         concat_points = (box_coords, box_labels)
 
         sparse_embeddings, dense_embeddings = self.model.sam_prompt_encoder(
             points=points,
-            boxes=bboxes,
+            boxes=None,
             masks=masks,
         )
         # Predict masks

{ultralytics-8.2.71 → ultralytics-8.2.72}/ultralytics/nn/modules/transformer.py

@@ -186,8 +186,8 @@ class MLP(nn.Module):
     def forward(self, x):
         """Forward pass for the entire MLP."""
         for i, layer in enumerate(self.layers):
-            x = self.act(layer(x)) if i < self.num_layers - 1 else layer(x)
-        return x.sigmoid() if self.sigmoid else x
+            x = getattr(self, "act", nn.ReLU())(layer(x)) if i < self.num_layers - 1 else layer(x)
+        return x.sigmoid() if getattr(self, "sigmoid", False) else x
 
 
 class LayerNorm2d(nn.Module):

{ultralytics-8.2.71 → ultralytics-8.2.72}/ultralytics/utils/downloads.py

@@ -41,7 +41,7 @@ def is_url(url, check=False):
     Args:
         url (str): The string to be validated as a URL.
         check (bool, optional): If True, performs an additional check to see if the URL exists online.
-            Defaults to True.
+            Defaults to False.
 
     Returns:
         (bool): Returns True for a valid URL. If 'check' is True, also returns True if the URL exists online.
@@ -201,7 +201,7 @@ def check_disk_space(url="https://ultralytics.com/assets/coco8.zip", path=Path.c
     Args:
         url (str, optional): The URL to the file. Defaults to 'https://ultralytics.com/assets/coco8.zip'.
         path (str | Path, optional): The path or drive to check the available free space on.
-        sf (float, optional): Safety factor, the multiplier for the required free space. Defaults to 2.0.
+        sf (float, optional): Safety factor, the multiplier for the required free space. Defaults to 1.5.
         hard (bool, optional): Whether to throw an error or not on insufficient disk space. Defaults to True.
 
     Returns:

{ultralytics-8.2.71 → ultralytics-8.2.72}/ultralytics/utils/ops.py

@@ -528,7 +528,7 @@ def ltwh2xywh(x):
 def xyxyxyxy2xywhr(x):
     """
     Convert batched Oriented Bounding Boxes (OBB) from [xy1, xy2, xy3, xy4] to [xywh, rotation]. Rotation values are
-    expected in degrees from 0 to 90.
+    returned in radians from 0 to pi/2.
 
     Args:
         x (numpy.ndarray | torch.Tensor): Input box corners [xy1, xy2, xy3, xy4] of shape (n, 8).
@@ -551,7 +551,7 @@ def xyxyxyxy2xywhr(x):
 def xywhr2xyxyxyxy(x):
     """
     Convert batched Oriented Bounding Boxes (OBB) from [xywh, rotation] to [xy1, xy2, xy3, xy4]. Rotation values should
-    be in degrees from 0 to 90.
+    be in radians from 0 to pi/2.
 
     Args:
         x (numpy.ndarray | torch.Tensor): Boxes in [cx, cy, w, h, rotation] format of shape (n, 5) or (b, n, 5).

{ultralytics-8.2.71 → ultralytics-8.2.72}/ultralytics/utils/plotting.py

@@ -195,12 +195,12 @@ class Annotator:
 
     def circle_label(self, box, label="", color=(128, 128, 128), txt_color=(255, 255, 255), margin=2):
         """
-        Draws a label with a background rectangle centered within a given bounding box.
+        Draws a label with a background circle centered within a given bounding box.
 
         Args:
             box (tuple): The bounding box coordinates (x1, y1, x2, y2).
             label (str): The text label to be displayed.
-            color (tuple, optional): The background color of the rectangle (R, G, B).
+            color (tuple, optional): The background color of the rectangle (B, G, R).
             txt_color (tuple, optional): The color of the text (R, G, B).
             margin (int, optional): The margin between the text and the rectangle border.
         """
@@ -242,7 +242,7 @@ class Annotator:
         Args:
             box (tuple): The bounding box coordinates (x1, y1, x2, y2).
             label (str): The text label to be displayed.
-            color (tuple, optional): The background color of the rectangle (R, G, B).
+            color (tuple, optional): The background color of the rectangle (B, G, R).
             txt_color (tuple, optional): The color of the text (R, G, B).
             margin (int, optional): The margin between the text and the rectangle border.
         """

{ultralytics-8.2.71 → ultralytics-8.2.72/ultralytics.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.2.71
+Version: 8.2.72
 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