dgenerate-ultralytics-headless 8.3.243__tar.gz → 8.3.249__tar.gz

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dgenerate-ultralytics-headless
-Version: 8.3.243
+Version: 8.3.249
 Summary: Automatically built Ultralytics package with python-opencv-headless dependency instead of python-opencv
 Author-email: Glenn Jocher <glenn.jocher@ultralytics.com>, Jing Qiu <jing.qiu@ultralytics.com>
 Maintainer-email: Ultralytics <hello@ultralytics.com>
@@ -57,7 +57,7 @@ Provides-Extra: export
 Requires-Dist: numpy<2.0.0; extra == "export"
 Requires-Dist: onnx>=1.12.0; platform_system != "Darwin" and extra == "export"
 Requires-Dist: onnx<1.18.0,>=1.12.0; platform_system == "Darwin" and extra == "export"
-Requires-Dist: onnxslim>=0.1.80; extra == "export"
+Requires-Dist: onnxslim>=0.1.82; extra == "export"
 Requires-Dist: coremltools>=9.0; (platform_system != "Windows" and python_version <= "3.13") and extra == "export"
 Requires-Dist: scikit-learn>=1.3.2; (platform_system != "Windows" and python_version <= "3.13") and extra == "export"
 Requires-Dist: openvino>=2024.0.0; extra == "export"

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/dgenerate_ultralytics_headless.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dgenerate-ultralytics-headless
-Version: 8.3.243
+Version: 8.3.249
 Summary: Automatically built Ultralytics package with python-opencv-headless dependency instead of python-opencv
 Author-email: Glenn Jocher <glenn.jocher@ultralytics.com>, Jing Qiu <jing.qiu@ultralytics.com>
 Maintainer-email: Ultralytics <hello@ultralytics.com>
@@ -57,7 +57,7 @@ Provides-Extra: export
 Requires-Dist: numpy<2.0.0; extra == "export"
 Requires-Dist: onnx>=1.12.0; platform_system != "Darwin" and extra == "export"
 Requires-Dist: onnx<1.18.0,>=1.12.0; platform_system == "Darwin" and extra == "export"
-Requires-Dist: onnxslim>=0.1.80; extra == "export"
+Requires-Dist: onnxslim>=0.1.82; extra == "export"
 Requires-Dist: coremltools>=9.0; (platform_system != "Windows" and python_version <= "3.13") and extra == "export"
 Requires-Dist: scikit-learn>=1.3.2; (platform_system != "Windows" and python_version <= "3.13") and extra == "export"
 Requires-Dist: openvino>=2024.0.0; extra == "export"

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/dgenerate_ultralytics_headless.egg-info/requires.txt

@@ -27,7 +27,7 @@ zensical>=0.0.15
 
 [export]
 numpy<2.0.0
-onnxslim>=0.1.80
+onnxslim>=0.1.82
 openvino>=2024.0.0
 tensorflow<=2.19.0,>=2.0.0
 tensorflowjs>=2.0.0

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/pyproject.toml

@@ -91,7 +91,7 @@ export = [
     "numpy<2.0.0", # TF 2.20 compatibility
     "onnx>=1.12.0; platform_system != 'Darwin'", # ONNX export
     "onnx>=1.12.0,<1.18.0; platform_system == 'Darwin'",  # TF inference hanging on MacOS (tested up to onnx==1.20.0)
-    "onnxslim>=0.1.80",
+    "onnxslim>=0.1.82",
     "coremltools>=9.0; platform_system != 'Windows' and python_version <= '3.13'", # CoreML supported on macOS and Linux
     "scikit-learn>=1.3.2; platform_system != 'Windows' and python_version <= '3.13'", # CoreML k-means quantization
     "openvino>=2024.0.0",  # OpenVINO export

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/tests/test_engine.py

@@ -13,7 +13,7 @@ from ultralytics.models.yolo import classify, detect, segment
 from ultralytics.utils import ASSETS, DEFAULT_CFG, WEIGHTS_DIR
 
 
-def test_func(*args):
+def test_func(*args, **kwargs):
     """Test function callback for evaluating YOLO model performance metrics."""
     print("callback test passed")
 

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/tests/test_exports.py

@@ -267,13 +267,13 @@ def test_export_imx():
 @pytest.mark.skipif(not checks.IS_PYTHON_3_10, reason="Axelera export requires Python 3.10")
 def test_export_axelera():
     """Test YOLO export to Axelera format."""
-    # For faster testing, use a smaller calibration dataset
-    # 32 image size crashes axelera export, so use 64
+    # For faster testing, use a smaller calibration dataset (32 image size crashes axelera export, so 64 is used)
     file = YOLO(MODEL).export(format="axelera", imgsz=64, data="coco8.yaml")
     assert Path(file).exists(), f"Axelera export failed, directory not found: {file}"
     shutil.rmtree(file, ignore_errors=True)  # cleanup
 
 
+# @pytest.mark.skipif(True, reason="Disabled for debugging ruamel.yaml installation required by executorch")
 @pytest.mark.skipif(not checks.IS_PYTHON_MINIMUM_3_10 or not TORCH_2_9, reason="Requires Python>=3.10 and Torch>=2.9.0")
 @pytest.mark.skipif(WINDOWS, reason="Skipping test on Windows")
 def test_export_executorch():

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.243"
+__version__ = "8.3.249"
 
 import importlib
 import os

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/cfg/models/rt-detr/rtdetr-l.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=rtdetr-l.yaml' will call rtdetr-l.yaml with scale 'l'
   # [depth, width, max_channels]
   l: [1.00, 1.00, 1024]
 

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/cfg/models/rt-detr/rtdetr-resnet101.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=rtdetr-resnet101.yaml' will call rtdetr-resnet101.yaml with scale 'l'
   # [depth, width, max_channels]
   l: [1.00, 1.00, 1024]
 

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/cfg/models/rt-detr/rtdetr-resnet50.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=rtdetr-resnet50.yaml' will call rtdetr-resnet50.yaml with scale 'l'
   # [depth, width, max_channels]
   l: [1.00, 1.00, 1024]
 

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/cfg/models/rt-detr/rtdetr-x.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=rtdetr-x.yaml' will call rtdetr-x.yaml with scale 'x'
   # [depth, width, max_channels]
   x: [1.00, 1.00, 2048]
 

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/cfg/models/v10/yolov10b.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' uses the 'n' scale
   # [depth, width, max_channels]
   b: [0.67, 1.00, 512]
 
@@ -24,7 +24,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv10.0n head
+# YOLOv10 head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/cfg/models/v10/yolov10l.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' uses the 'n' scale
   # [depth, width, max_channels]
   l: [1.00, 1.00, 512]
 
@@ -24,7 +24,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv10.0n head
+# YOLOv10 head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/cfg/models/v10/yolov10m.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' uses the 'n' scale
   # [depth, width, max_channels]
   m: [0.67, 0.75, 768]
 
@@ -24,7 +24,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv10.0n head
+# YOLOv10 head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/cfg/models/v10/yolov10n.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' uses the 'n' scale
   # [depth, width, max_channels]
   n: [0.33, 0.25, 1024]
 
@@ -24,7 +24,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv10.0n head
+# YOLOv10 head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/cfg/models/v10/yolov10s.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' uses the 'n' scale
   # [depth, width, max_channels]
   s: [0.33, 0.50, 1024]
 
@@ -24,7 +24,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv10.0n head
+# YOLOv10 head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/cfg/models/v10/yolov10x.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' uses the 'n' scale
   # [depth, width, max_channels]
   x: [1.00, 1.25, 512]
 
@@ -24,7 +24,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv10.0n head
+# YOLOv10 head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/cfg/models/v3/yolov3-tiny.yaml

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# Ultralytics YOLOv3-tiiny object detection model with P4/16 - P5/32 outputs
+# Ultralytics YOLOv3-tiny object detection model with P4/16 - P5/32 outputs
 # Model docs: https://docs.ultralytics.com/models/yolov3
 # Task docs: https://docs.ultralytics.com/tasks/detect
 

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/cfg/models/v6/yolov6.yaml

@@ -7,7 +7,7 @@
 # Parameters
 nc: 80 # number of classes
 activation: torch.nn.ReLU() # (optional) model default activation function
-scales: # model compound scaling constants, i.e. 'model=yolov6n.yaml' will call yolov8.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov6n.yaml' will call yolov6.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.33, 0.25, 1024]
   s: [0.33, 0.50, 1024]

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/cfg/models/v8/yolov8-seg-p6.yaml

@@ -56,4 +56,4 @@ head:
   - [[-1, 11], 1, Concat, [1]] # cat head P6
   - [-1, 3, C2, [1024, False]] # 29 (P6/64-xlarge)
 
-  - [[20, 23, 26, 29], 1, Segment, [nc, 32, 256]] # Pose(P3, P4, P5, P6)
+  - [[20, 23, 26, 29], 1, Segment, [nc, 32, 256]] # Segment(P3, P4, P5, P6)

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/cfg/models/v9/yolov9s.yaml

@@ -38,4 +38,4 @@ head:
   - [[-1, 9], 1, Concat, [1]] # cat head P5
   - [-1, 1, RepNCSPELAN4, [256, 256, 128, 3]] # 21 (P5/32-large)
 
-  - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4 P5)
+  - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/data/converter.py

@@ -353,7 +353,7 @@ def convert_segment_masks_to_yolo_seg(masks_dir: str, output_dir: str, classes:
     Args:
         masks_dir (str): The path to the directory where all mask images (png, jpg) are stored.
         output_dir (str): The path to the directory where the converted YOLO segmentation masks will be stored.
-        classes (int): Total classes in the dataset i.e. for COCO classes=80
+        classes (int): Total number of classes in the dataset, e.g., 80 for COCO.
 
     Examples:
         >>> from ultralytics.data.converter import convert_segment_masks_to_yolo_seg

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/engine/exporter.py

@@ -87,6 +87,7 @@ from ultralytics.utils import (
     IS_COLAB,
     IS_DEBIAN_BOOKWORM,
     IS_DEBIAN_TRIXIE,
+    IS_DOCKER,
     IS_JETSON,
     IS_RASPBERRYPI,
     IS_UBUNTU,
@@ -1187,10 +1188,13 @@ class Exporter:
         """
         LOGGER.info(f"\n{prefix} starting export with ExecuTorch...")
         assert TORCH_2_9, f"ExecuTorch export requires torch>=2.9.0 but torch=={TORCH_VERSION} is installed"
-        # TorchAO release compatibility table bug https://github.com/pytorch/ao/issues/2919
-        # Setuptools bug: https://github.com/pypa/setuptools/issues/4483
-        check_requirements("setuptools<71.0.0")  # Setuptools bug: https://github.com/pypa/setuptools/issues/4483
-        check_requirements(("executorch==1.0.1", "flatbuffers"))
+
+        # BUG executorch build on arm64 Docker requires packaging>=22.0 https://github.com/pypa/setuptools/issues/4483
+        if LINUX and ARM64 and IS_DOCKER:
+            check_requirements("packaging>=22.0")
+
+        check_requirements("ruamel.yaml<0.19.0")
+        check_requirements("executorch==1.0.1", "flatbuffers")
         # Pin numpy to avoid coremltools errors with numpy>=2.4.0, must be separate
         check_requirements("numpy<=2.3.5")
 

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/engine/model.py

@@ -523,7 +523,7 @@ class Model(torch.nn.Module):
         args = {**self.overrides, **custom, **kwargs}  # highest priority args on the right
         prompts = args.pop("prompts", None)  # for SAM-type models
 
-        if not self.predictor:
+        if not self.predictor or self.predictor.args.device != args.get("device", self.predictor.args.device):
             self.predictor = (predictor or self._smart_load("predictor"))(overrides=args, _callbacks=self.callbacks)
             self.predictor.setup_model(model=self.model, verbose=is_cli)
         else:  # only update args if predictor is already setup

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/engine/results.py

@@ -954,8 +954,8 @@ class Boxes(BaseTensor):
             >>> boxes = Boxes(torch.tensor([[100, 50, 150, 100], [200, 150, 300, 250]]), orig_shape=(480, 640))
             >>> xywh = boxes.xywh
             >>> print(xywh)
-            tensor([[100.0000,  50.0000,  50.0000,  50.0000],
-                    [200.0000, 150.0000, 100.0000, 100.0000]])
+            tensor([[125.0000,  75.0000,  50.0000,  50.0000],
+                    [250.0000, 200.0000, 100.0000, 100.0000]])
         """
         return ops.xyxy2xywh(self.xyxy)
 

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/engine/validator.py

@@ -364,7 +364,10 @@ class BaseValidator:
         return []
 
     def on_plot(self, name, data=None):
-        """Register plots for visualization."""
+        """Register plots for visualization, deduplicating by type."""
+        plot_type = data.get("type") if data else None
+        if plot_type and any((v.get("data") or {}).get("type") == plot_type for v in self.plots.values()):
+            return  # Skip duplicate plot types
         self.plots[Path(name)] = {"data": data, "timestamp": time.time()}
 
     def plot_val_samples(self, batch, ni):

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/models/sam/modules/utils.py

@@ -166,7 +166,7 @@ def reshape_for_broadcast(freqs_cis: torch.Tensor, x: torch.Tensor):
         AssertionError: If the shape of freqs_cis doesn't match the last two dimensions of x.
     """
     ndim = x.ndim
-    assert 0 <= 1 < ndim
+    assert ndim >= 2
     assert freqs_cis.shape == (x.shape[-2], x.shape[-1])
     shape = [d if i >= ndim - 2 else 1 for i, d in enumerate(x.shape)]
     return freqs_cis.view(*shape)

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/models/yolo/detect/val.py

@@ -347,14 +347,14 @@ class DetectionValidator(BaseValidator):
             ni (int): Batch index.
             max_det (Optional[int]): Maximum number of detections to plot.
         """
-        # TODO: optimize this
+        if not preds:
+            return
         for i, pred in enumerate(preds):
             pred["batch_idx"] = torch.ones_like(pred["conf"]) * i  # add batch index to predictions
         keys = preds[0].keys()
         max_det = max_det or self.args.max_det
         batched_preds = {k: torch.cat([x[k][:max_det] for x in preds], dim=0) for k in keys}
-        # TODO: fix this
-        batched_preds["bboxes"][:, :4] = ops.xyxy2xywh(batched_preds["bboxes"][:, :4])  # convert to xywh format
+        batched_preds["bboxes"] = ops.xyxy2xywh(batched_preds["bboxes"])  # convert to xywh format
         plot_images(
             images=batch["img"],
             labels=batched_preds,

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/models/yolo/segment/predict.py

@@ -98,9 +98,9 @@ class SegmentationPredictor(DetectionPredictor):
             masks = None
         elif self.args.retina_masks:
             pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
-            masks = ops.process_mask_native(proto, pred[:, 6:], pred[:, :4], orig_img.shape[:2])  # HWC
+            masks = ops.process_mask_native(proto, pred[:, 6:], pred[:, :4], orig_img.shape[:2])  # NHW
         else:
-            masks = ops.process_mask(proto, pred[:, 6:], pred[:, :4], img.shape[2:], upsample=True)  # HWC
+            masks = ops.process_mask(proto, pred[:, 6:], pred[:, :4], img.shape[2:], upsample=True)  # NHW
             pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
         if masks is not None:
             keep = masks.amax((-2, -1)) > 0  # only keep predictions with masks

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/nn/modules/head.py

@@ -1078,9 +1078,9 @@ class RTDETRDecoder(nn.Module):
         enc_outputs_scores = self.enc_score_head(features)  # (bs, h*w, nc)
 
         # Query selection
-        # (bs, num_queries)
+        # (bs*num_queries,)
         topk_ind = torch.topk(enc_outputs_scores.max(-1).values, self.num_queries, dim=1).indices.view(-1)
-        # (bs, num_queries)
+        # (bs*num_queries,)
         batch_ind = torch.arange(end=bs, dtype=topk_ind.dtype).unsqueeze(-1).repeat(1, self.num_queries).view(-1)
 
         # (bs, num_queries, 256)

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/nn/modules/transformer.py

@@ -305,16 +305,16 @@ class TransformerBlock(nn.Module):
         """Forward propagate the input through the transformer block.
 
         Args:
-            x (torch.Tensor): Input tensor with shape [b, c1, w, h].
+            x (torch.Tensor): Input tensor with shape [b, c1, h, w].
 
         Returns:
-            (torch.Tensor): Output tensor with shape [b, c2, w, h].
+            (torch.Tensor): Output tensor with shape [b, c2, h, w].
         """
         if self.conv is not None:
             x = self.conv(x)
-        b, _, w, h = x.shape
+        b, _, h, w = x.shape
         p = x.flatten(2).permute(2, 0, 1)
-        return self.tr(p + self.linear(p)).permute(1, 2, 0).reshape(b, self.c2, w, h)
+        return self.tr(p + self.linear(p)).permute(1, 2, 0).reshape(b, self.c2, h, w)
 
 
 class MLPBlock(nn.Module):

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/nn/modules/utils.py

@@ -147,7 +147,7 @@ def multi_scale_deformable_attn_pytorch(
         sampling_value_list.append(sampling_value_l_)
     # (bs, num_queries, num_heads, num_levels, num_points) ->
     # (bs, num_heads, num_queries, num_levels, num_points) ->
-    # (bs, num_heads, 1, num_queries, num_levels*num_points)
+    # (bs*num_heads, 1, num_queries, num_levels*num_points)
     attention_weights = attention_weights.transpose(1, 2).reshape(
         bs * num_heads, 1, num_queries, num_levels * num_points
     )

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/nn/tasks.py

@@ -407,7 +407,7 @@ class DetectionModel(BaseModel):
             self.model.train()  # Set model back to training(default) mode
             m.bias_init()  # only run once
         else:
-            self.stride = torch.Tensor([32])  # default stride for i.e. RTDETR
+            self.stride = torch.Tensor([32])  # default stride, e.g., RTDETR
 
         # Init weights, biases
         initialize_weights(self)
@@ -1589,7 +1589,7 @@ def parse_model(d, ch, verbose=True):
         n = n_ = max(round(n * depth), 1) if n > 1 else n  # depth gain
         if m in base_modules:
             c1, c2 = ch[f], args[0]
-            if c2 != nc:  # if c2 not equal to number of classes (i.e. for Classify() output)
+            if c2 != nc:  # if c2 != nc (e.g., Classify() output)
                 c2 = make_divisible(min(c2, max_channels) * width, 8)
             if m is C2fAttn:  # set 1) embed channels and 2) num heads
                 args[1] = make_divisible(min(args[1], max_channels // 2) * width, 8)

{dgenerate_ultralytics_headless-8.3.243 → dgenerate_ultralytics_headless-8.3.249}/ultralytics/solutions/object_counter.py

@@ -129,7 +129,7 @@ class ObjectCounter(BaseSolution):
             str.capitalize(key): f"{'IN ' + str(value['IN']) if self.show_in else ''} "
             f"{'OUT ' + str(value['OUT']) if self.show_out else ''}".strip()
             for key, value in self.classwise_count.items()
-            if value["IN"] != 0 or (value["OUT"] != 0 and (self.show_in or self.show_out))
+            if (value["IN"] != 0 and self.show_in) or (value["OUT"] != 0 and self.show_out)
         }
         if labels_dict:
             self.annotator.display_analytics(plot_im, labels_dict, (104, 31, 17), (255, 255, 255), self.margin)