dgenerate-ultralytics-headless 8.3.137__py3-none-any.whl → 8.3.224__py3-none-any.whl

ultralytics/cfg/trackers/botsort.yaml

@@ -1,22 +1,21 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# Default Ultralytics settings for BoT-SORT tracker when using mode="track"
-# For documentation and examples see https://docs.ultralytics.com/modes/track/
-# For BoT-SORT source code see https://github.com/NirAharon/BoT-SORT
+# BoT-SORT tracker defaults for mode="track"
+# Docs: https://docs.ultralytics.com/modes/track/
 
-tracker_type: botsort # tracker type, ['botsort', 'bytetrack']
-track_high_thresh: 0.25 # threshold for the first association
-track_low_thresh: 0.1 # threshold for the second association
-new_track_thresh: 0.25 # threshold for init new track if the detection does not match any tracks
-track_buffer: 30 # buffer to calculate the time when to remove tracks
-match_thresh: 0.8 # threshold for matching tracks
-fuse_score: True # Whether to fuse confidence scores with the iou distances before matching
-# min_box_area: 10  # threshold for min box areas(for tracker evaluation, not used for now)
+tracker_type: botsort # (str) Tracker backend: botsort|bytetrack; choose botsort to enable BoT-SORT features
+track_high_thresh: 0.25 # (float) First-stage match threshold; raise for cleaner tracks, lower to keep more
+track_low_thresh: 0.1 # (float) Second-stage threshold for low-score matches; balances recovery vs drift
+new_track_thresh: 0.25 # (float) Start a new track if no match ≥ this; higher reduces false tracks
+track_buffer: 30 # (int) Frames to keep lost tracks alive; higher handles occlusion, increases ID switches risk
+match_thresh: 0.8 # (float) Association similarity threshold (IoU/cost); tune with detector quality
+fuse_score: True # (bool) Fuse detection score with motion/IoU for matching; stabilizes weak detections
+
+# BoT-SORT specifics
+gmc_method: sparseOptFlow # (str) Global motion compensation: sparseOptFlow|orb|none; helps moving camera scenes
 
-# BoT-SORT settings
-gmc_method: sparseOptFlow # method of global motion compensation
 # ReID model related thresh
-proximity_thresh: 0.5 # minimum IoU for valid match with ReID
-appearance_thresh: 0.8 # minimum appearance similarity for ReID
-with_reid: False
-model: auto # uses native features if detector is YOLO else yolo11n-cls.pt
+proximity_thresh: 0.5 # (float) Min IoU to consider tracks proximate for ReID; higher is stricter
+appearance_thresh: 0.8 # (float) Min appearance similarity for ReID; raise to avoid identity swaps
+with_reid: False # (bool) Enable ReID model use; needs extra model and compute
+model: auto # (str) ReID model name/path; "auto" uses detector features if available

ultralytics/cfg/trackers/bytetrack.yaml

@@ -1,14 +1,12 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# Default Ultralytics settings for ByteTrack tracker when using mode="track"
-# For documentation and examples see https://docs.ultralytics.com/modes/track/
-# For ByteTrack source code see https://github.com/ifzhang/ByteTrack
+# ByteTrack tracker defaults for mode="track"
+# Docs: https://docs.ultralytics.com/modes/track/
 
-tracker_type: bytetrack # tracker type, ['botsort', 'bytetrack']
-track_high_thresh: 0.25 # threshold for the first association
-track_low_thresh: 0.1 # threshold for the second association
-new_track_thresh: 0.25 # threshold for init new track if the detection does not match any tracks
-track_buffer: 30 # buffer to calculate the time when to remove tracks
-match_thresh: 0.8 # threshold for matching tracks
-fuse_score: True # Whether to fuse confidence scores with the iou distances before matching
-# min_box_area: 10  # threshold for min box areas(for tracker evaluation, not used for now)
+tracker_type: bytetrack # (str) Tracker backend: botsort|bytetrack; choose bytetrack for the classic baseline
+track_high_thresh: 0.25 # (float) First-stage match threshold; raise for cleaner tracks, lower to keep more
+track_low_thresh: 0.1 # (float) Second-stage threshold for low-score matches; balances recovery vs drift
+new_track_thresh: 0.25 # (float) Start a new track if no match ≥ this; higher reduces false tracks
+track_buffer: 30 # (int) Frames to keep lost tracks alive; higher handles occlusion, increases ID switches risk
+match_thresh: 0.8 # (float) Association similarity threshold (IoU/cost); tune with detector quality
+fuse_score: True # (bool) Fuse detection score with motion/IoU for matching; stabilizes weak detections

ultralytics/data/__init__.py

@@ -14,13 +14,13 @@ from .dataset import (
 __all__ = (
     "BaseDataset",
     "ClassificationDataset",
+    "GroundingDataset",
     "SemanticDataset",
+    "YOLOConcatDataset",
     "YOLODataset",
     "YOLOMultiModalDataset",
-    "YOLOConcatDataset",
-    "GroundingDataset",
-    "build_yolo_dataset",
-    "build_grounding",
     "build_dataloader",
+    "build_grounding",
+    "build_yolo_dataset",
     "load_inference_source",
 )

ultralytics/data/annotator.py

@@ -1,13 +1,14 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+from __future__ import annotations
+
 from pathlib import Path
-from typing import List, Optional, Union
 
 from ultralytics import SAM, YOLO
 
 
 def auto_annotate(
-    data: Union[str, Path],
+    data: str | Path,
     det_model: str = "yolo11x.pt",
     sam_model: str = "sam_b.pt",
     device: str = "",
@@ -15,26 +16,26 @@ def auto_annotate(
     iou: float = 0.45,
     imgsz: int = 640,
     max_det: int = 300,
-    classes: Optional[List[int]] = None,
-    output_dir: Optional[Union[str, Path]] = None,
+    classes: list[int] | None = None,
+    output_dir: str | Path | None = None,
 ) -> None:
-    """
-    Automatically annotate images using a YOLO object detection model and a SAM segmentation model.
+    """Automatically annotate images using a YOLO object detection model and a SAM segmentation model.
 
     This function processes images in a specified directory, detects objects using a YOLO model, and then generates
-    segmentation masks using a SAM model. The resulting annotations are saved as text files.
+    segmentation masks using a SAM model. The resulting annotations are saved as text files in YOLO format.
 
     Args:
         data (str | Path): Path to a folder containing images to be annotated.
         det_model (str): Path or name of the pre-trained YOLO detection model.
         sam_model (str): Path or name of the pre-trained SAM segmentation model.
-        device (str): Device to run the models on (e.g., 'cpu', 'cuda', '0').
+        device (str): Device to run the models on (e.g., 'cpu', 'cuda', '0'). Empty string for auto-selection.
         conf (float): Confidence threshold for detection model.
         iou (float): IoU threshold for filtering overlapping boxes in detection results.
         imgsz (int): Input image resize dimension.
         max_det (int): Maximum number of detections per image.
-        classes (List[int] | None): Filter predictions to specified class IDs, returning only relevant detections.
-        output_dir (str | Path | None): Directory to save the annotated results. If None, a default directory is created.
+        classes (list[int], optional): Filter predictions to specified class IDs, returning only relevant detections.
+        output_dir (str | Path, optional): Directory to save the annotated results. If None, creates a default directory
+            based on the input data path.
 
     Examples:
         >>> from ultralytics.data.annotator import auto_annotate
@@ -53,8 +54,7 @@ def auto_annotate(
     )
 
     for result in det_results:
-        class_ids = result.boxes.cls.int().tolist()  # noqa
-        if class_ids:
+        if class_ids := result.boxes.cls.int().tolist():  # Extract class IDs from detection results
             boxes = result.boxes.xyxy  # Boxes object for bbox outputs
             sam_results = sam_model(result.orig_img, bboxes=boxes, verbose=False, save=False, device=device)
             segments = sam_results[0].masks.xyn