ultralytics 8.1.29__py3-none-any.whl → 8.3.63__py3-none-any.whl

ultralytics/cfg/models/v9/yolov9e.yaml

@@ -1,60 +1,64 @@
-# YOLOv9
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# parameters
-nc: 80  # number of classes
+# YOLOv9e object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolov9
+# Task docs: https://docs.ultralytics.com/tasks/detect
+# 1225 layers, 58206592 parameters, 193.0 GFLOPs
 
-# gelan backbone
+# Parameters
+nc: 80 # number of classes
+
+# GELAN backbone
 backbone:
-  - [-1, 1, Silence, []]
-  - [-1, 1, Conv, [64, 3, 2]]  # 1-P1/2
-  - [-1, 1, Conv, [128, 3, 2]]  # 2-P2/4
-  - [-1, 1, RepNCSPELAN4, [256, 128, 64, 2]]  # 3
-  - [-1, 1, ADown, [256]]  # 4-P3/8
-  - [-1, 1, RepNCSPELAN4, [512, 256, 128, 2]]  # 5
-  - [-1, 1, ADown, [512]]  # 6-P4/16
-  - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]]  # 7
-  - [-1, 1, ADown, [1024]]  # 8-P5/32
-  - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]]  # 9
-   
+  - [-1, 1, nn.Identity, []]
+  - [-1, 1, Conv, [64, 3, 2]] # 1-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 2-P2/4
+  - [-1, 1, RepNCSPELAN4, [256, 128, 64, 2]] # 3
+  - [-1, 1, ADown, [256]] # 4-P3/8
+  - [-1, 1, RepNCSPELAN4, [512, 256, 128, 2]] # 5
+  - [-1, 1, ADown, [512]] # 6-P4/16
+  - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 7
+  - [-1, 1, ADown, [1024]] # 8-P5/32
+  - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 9
+
   - [1, 1, CBLinear, [[64]]] # 10
   - [3, 1, CBLinear, [[64, 128]]] # 11
   - [5, 1, CBLinear, [[64, 128, 256]]] # 12
   - [7, 1, CBLinear, [[64, 128, 256, 512]]] # 13
   - [9, 1, CBLinear, [[64, 128, 256, 512, 1024]]] # 14
-  
-  - [0, 1, Conv, [64, 3, 2]]  # 15-P1/2
+
+  - [0, 1, Conv, [64, 3, 2]] # 15-P1/2
   - [[10, 11, 12, 13, 14, -1], 1, CBFuse, [[0, 0, 0, 0, 0]]] # 16
-  - [-1, 1, Conv, [128, 3, 2]]  # 17-P2/4
-  - [[11, 12, 13, 14, -1], 1, CBFuse, [[1, 1, 1, 1]]] # 18  
-  - [-1, 1, RepNCSPELAN4, [256, 128, 64, 2]]  # 19
-  - [-1, 1, ADown, [256]]  # 20-P3/8
-  - [[12, 13, 14, -1], 1, CBFuse, [[2, 2, 2]]] # 21  
-  - [-1, 1, RepNCSPELAN4, [512, 256, 128, 2]]  # 22
-  - [-1, 1, ADown, [512]]  # 23-P4/16
-  - [[13, 14, -1], 1, CBFuse, [[3, 3]]] # 24 
-  - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]]  # 25
-  - [-1, 1, ADown, [1024]]  # 26-P5/32
+  - [-1, 1, Conv, [128, 3, 2]] # 17-P2/4
+  - [[11, 12, 13, 14, -1], 1, CBFuse, [[1, 1, 1, 1]]] # 18
+  - [-1, 1, RepNCSPELAN4, [256, 128, 64, 2]] # 19
+  - [-1, 1, ADown, [256]] # 20-P3/8
+  - [[12, 13, 14, -1], 1, CBFuse, [[2, 2, 2]]] # 21
+  - [-1, 1, RepNCSPELAN4, [512, 256, 128, 2]] # 22
+  - [-1, 1, ADown, [512]] # 23-P4/16
+  - [[13, 14, -1], 1, CBFuse, [[3, 3]]] # 24
+  - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 25
+  - [-1, 1, ADown, [1024]] # 26-P5/32
   - [[14, -1], 1, CBFuse, [[4]]] # 27
-  - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]]  # 28
-  - [-1, 1, SPPELAN, [512, 256]]  # 29
+  - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 28
+  - [-1, 1, SPPELAN, [512, 256]] # 29
 
-# gelan head
+# GELAN head
 head:
-  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
-  - [[-1, 25], 1, Concat, [1]]  # cat backbone P4
-  - [-1, 1, RepNCSPELAN4, [512, 512, 256, 2]]  # 32
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 25], 1, Concat, [1]] # cat backbone P4
+  - [-1, 1, RepNCSPELAN4, [512, 512, 256, 2]] # 32
 
-  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
-  - [[-1, 22], 1, Concat, [1]]  # cat backbone P3
-  - [-1, 1, RepNCSPELAN4, [256, 256, 128, 2]]  # 35 (P3/8-small)
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 22], 1, Concat, [1]] # cat backbone P3
+  - [-1, 1, RepNCSPELAN4, [256, 256, 128, 2]] # 35 (P3/8-small)
 
   - [-1, 1, ADown, [256]]
-  - [[-1, 32], 1, Concat, [1]]  # cat head P4
-  - [-1, 1, RepNCSPELAN4, [512, 512, 256, 2]]  # 38 (P4/16-medium)
+  - [[-1, 32], 1, Concat, [1]] # cat head P4
+  - [-1, 1, RepNCSPELAN4, [512, 512, 256, 2]] # 38 (P4/16-medium)
 
   - [-1, 1, ADown, [512]]
-  - [[-1, 29], 1, Concat, [1]]  # cat head P5
-  - [-1, 1, RepNCSPELAN4, [512, 1024, 512, 2]]  # 41 (P5/32-large)
+  - [[-1, 29], 1, Concat, [1]] # cat head P5
+  - [-1, 1, RepNCSPELAN4, [512, 1024, 512, 2]] # 41 (P5/32-large)
 
-   # detect
-  - [[35, 38, 41], 1, Detect, [nc]]  # Detect(P3, P4, P5)
+  - [[35, 38, 41], 1, Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v9/yolov9m.yaml

@@ -0,0 +1,41 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLOv9m object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolov9
+# Task docs: https://docs.ultralytics.com/tasks/detect
+# 603 layers, 20216160 parameters, 77.9 GFLOPs
+
+# Parameters
+nc: 80 # number of classes
+
+# GELAN backbone
+backbone:
+  - [-1, 1, Conv, [32, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [64, 3, 2]] # 1-P2/4
+  - [-1, 1, RepNCSPELAN4, [128, 128, 64, 1]] # 2
+  - [-1, 1, AConv, [240]] # 3-P3/8
+  - [-1, 1, RepNCSPELAN4, [240, 240, 120, 1]] # 4
+  - [-1, 1, AConv, [360]] # 5-P4/16
+  - [-1, 1, RepNCSPELAN4, [360, 360, 180, 1]] # 6
+  - [-1, 1, AConv, [480]] # 7-P5/32
+  - [-1, 1, RepNCSPELAN4, [480, 480, 240, 1]] # 8
+  - [-1, 1, SPPELAN, [480, 240]] # 9
+
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 1, RepNCSPELAN4, [360, 360, 180, 1]] # 12
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 1, RepNCSPELAN4, [240, 240, 120, 1]] # 15
+
+  - [-1, 1, AConv, [180]]
+  - [[-1, 12], 1, Concat, [1]] # cat head P4
+  - [-1, 1, RepNCSPELAN4, [360, 360, 180, 1]] # 18 (P4/16-medium)
+
+  - [-1, 1, AConv, [240]]
+  - [[-1, 9], 1, Concat, [1]] # cat head P5
+  - [-1, 1, RepNCSPELAN4, [480, 480, 240, 1]] # 21 (P5/32-large)
+
+  - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v9/yolov9s.yaml

@@ -0,0 +1,41 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLOv9s object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolov9
+# Task docs: https://docs.ultralytics.com/tasks/detect
+# 917 layers, 7318368 parameters, 27.6 GFLOPs
+
+# Parameters
+nc: 80 # number of classes
+
+# GELAN backbone
+backbone:
+  - [-1, 1, Conv, [32, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [64, 3, 2]] # 1-P2/4
+  - [-1, 1, ELAN1, [64, 64, 32]] # 2
+  - [-1, 1, AConv, [128]] # 3-P3/8
+  - [-1, 1, RepNCSPELAN4, [128, 128, 64, 3]] # 4
+  - [-1, 1, AConv, [192]] # 5-P4/16
+  - [-1, 1, RepNCSPELAN4, [192, 192, 96, 3]] # 6
+  - [-1, 1, AConv, [256]] # 7-P5/32
+  - [-1, 1, RepNCSPELAN4, [256, 256, 128, 3]] # 8
+  - [-1, 1, SPPELAN, [256, 128]] # 9
+
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 1, RepNCSPELAN4, [192, 192, 96, 3]] # 12
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 1, RepNCSPELAN4, [128, 128, 64, 3]] # 15
+
+  - [-1, 1, AConv, [96]]
+  - [[-1, 12], 1, Concat, [1]] # cat head P4
+  - [-1, 1, RepNCSPELAN4, [192, 192, 96, 3]] # 18 (P4/16-medium)
+
+  - [-1, 1, AConv, [128]]
+  - [[-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)

ultralytics/cfg/models/v9/yolov9t.yaml

@@ -0,0 +1,41 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLOv9t object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolov9
+# Task docs: https://docs.ultralytics.com/tasks/detect
+# 917 layers, 2128720 parameters, 8.5 GFLOPs
+
+# Parameters
+nc: 80 # number of classes
+
+# GELAN backbone
+backbone:
+  - [-1, 1, Conv, [16, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [32, 3, 2]] # 1-P2/4
+  - [-1, 1, ELAN1, [32, 32, 16]] # 2
+  - [-1, 1, AConv, [64]] # 3-P3/8
+  - [-1, 1, RepNCSPELAN4, [64, 64, 32, 3]] # 4
+  - [-1, 1, AConv, [96]] # 5-P4/16
+  - [-1, 1, RepNCSPELAN4, [96, 96, 48, 3]] # 6
+  - [-1, 1, AConv, [128]] # 7-P5/32
+  - [-1, 1, RepNCSPELAN4, [128, 128, 64, 3]] # 8
+  - [-1, 1, SPPELAN, [128, 64]] # 9
+
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 1, RepNCSPELAN4, [96, 96, 48, 3]] # 12
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 1, RepNCSPELAN4, [64, 64, 32, 3]] # 15
+
+  - [-1, 1, AConv, [48]]
+  - [[-1, 12], 1, Concat, [1]] # cat head P4
+  - [-1, 1, RepNCSPELAN4, [96, 96, 48, 3]] # 18 (P4/16-medium)
+
+  - [-1, 1, AConv, [64]]
+  - [[-1, 9], 1, Concat, [1]] # cat head P5
+  - [-1, 1, RepNCSPELAN4, [128, 128, 64, 3]] # 21 (P5/32-large)
+
+  - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/solutions/default.yaml

@@ -0,0 +1,24 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Global configuration YAML with settings and arguments for Ultralytics Solutions
+# For documentation see https://docs.ultralytics.com/solutions/
+
+# Object counting settings  --------------------------------------------------------------------------------------------
+region: # list[tuple[int, int]] object counting, queue or speed estimation region points.
+show_in: True # (bool) flag to display objects moving *into* the defined region
+show_out: True # (bool) flag to display objects moving *out of* the defined region
+
+# Heatmaps settings ----------------------------------------------------------------------------------------------------
+colormap: #  (int | str) colormap for heatmap, Only OPENCV supported colormaps can be used.
+
+# Workouts monitoring settings -----------------------------------------------------------------------------------------
+up_angle: 145.0 # (float) Workouts up_angle for counts, 145.0 is default value.
+down_angle: 90 # (float) Workouts down_angle for counts, 90 is default value. Y
+kpts: [6, 8, 10] # (list[int]) keypoints for workouts monitoring, i.e. for push-ups kpts have values of [6, 8, 10].
+
+# Analytics settings ---------------------------------------------------------------------------------------------------
+analytics_type: "line" # (str) analytics type i.e "line", "pie", "bar" or "area" charts.
+json_file: # (str) parking system regions file path.
+
+# Security alarm system settings ---------------------------------------------------------------------------------------
+records: 5 # (int) Total detections count to send an email about security

ultralytics/cfg/trackers/botsort.yaml

@@ -1,14 +1,17 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
-# Default YOLO tracker settings for BoT-SORT tracker https://github.com/NirAharon/BoT-SORT
+# 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
 
 tracker_type: botsort # tracker type, ['botsort', 'bytetrack']
-track_high_thresh: 0.5 # threshold for the first association
+track_high_thresh: 0.25 # threshold for the first association
 track_low_thresh: 0.1 # threshold for the second association
-new_track_thresh: 0.6 # threshold for init new track if the detection does not match any tracks
+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)
-# mot20: False  # for tracker evaluation(not used for now)
 
 # BoT-SORT settings
 gmc_method: sparseOptFlow # method of global motion compensation

ultralytics/cfg/trackers/bytetrack.yaml

@@ -1,11 +1,14 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
-# Default YOLO tracker settings for ByteTrack tracker https://github.com/ifzhang/ByteTrack
+# 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
 
 tracker_type: bytetrack # tracker type, ['botsort', 'bytetrack']
-track_high_thresh: 0.5 # threshold for the first association
+track_high_thresh: 0.25 # threshold for the first association
 track_low_thresh: 0.1 # threshold for the second association
-new_track_thresh: 0.6 # threshold for init new track if the detection does not match any tracks
+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)
-# mot20: False  # for tracker evaluation(not used for now)

ultralytics/data/__init__.py

@@ -1,15 +1,26 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 from .base import BaseDataset
-from .build import build_dataloader, build_yolo_dataset, load_inference_source
-from .dataset import ClassificationDataset, SemanticDataset, YOLODataset
+from .build import build_dataloader, build_grounding, build_yolo_dataset, load_inference_source
+from .dataset import (
+    ClassificationDataset,
+    GroundingDataset,
+    SemanticDataset,
+    YOLOConcatDataset,
+    YOLODataset,
+    YOLOMultiModalDataset,
+)
 
 __all__ = (
     "BaseDataset",
     "ClassificationDataset",
     "SemanticDataset",
     "YOLODataset",
+    "YOLOMultiModalDataset",
+    "YOLOConcatDataset",
+    "GroundingDataset",
     "build_yolo_dataset",
+    "build_grounding",
     "build_dataloader",
     "load_inference_source",
 )

ultralytics/data/annotator.py

@@ -1,28 +1,48 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 from pathlib import Path
 
 from ultralytics import SAM, YOLO
 
 
-def auto_annotate(data, det_model="yolov8x.pt", sam_model="sam_b.pt", device="", output_dir=None):
+def auto_annotate(
+    data,
+    det_model="yolo11x.pt",
+    sam_model="sam_b.pt",
+    device="",
+    conf=0.25,
+    iou=0.45,
+    imgsz=640,
+    max_det=300,
+    classes=None,
+    output_dir=None,
+):
     """
     Automatically annotates 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.
+
     Args:
         data (str): Path to a folder containing images to be annotated.
-        det_model (str, optional): Pre-trained YOLO detection model. Defaults to 'yolov8x.pt'.
-        sam_model (str, optional): Pre-trained SAM segmentation model. Defaults to 'sam_b.pt'.
-        device (str, optional): Device to run the models on. Defaults to an empty string (CPU or GPU, if available).
-        output_dir (str | None | optional): Directory to save the annotated results.
-            Defaults to a 'labels' folder in the same directory as 'data'.
-
-    Example:
-        ```python
-        from ultralytics.data.annotator import auto_annotate
-
-        auto_annotate(data='ultralytics/assets', det_model='yolov8n.pt', sam_model='mobile_sam.pt')
-        ```
+        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').
+        conf (float): Confidence threshold for detection model; default is 0.25.
+        iou (float): IoU threshold for filtering overlapping boxes in detection results; default is 0.45.
+        imgsz (int): Input image resize dimension; default is 640.
+        max_det (int): Limits detections per image to control outputs in dense scenes.
+        classes (list): Filters predictions to specified class IDs, returning only relevant detections.
+        output_dir (str | None): Directory to save the annotated results. If None, a default directory is created.
+
+    Examples:
+        >>> from ultralytics.data.annotator import auto_annotate
+        >>> auto_annotate(data="ultralytics/assets", det_model="yolo11n.pt", sam_model="mobile_sam.pt")
+
+    Notes:
+        - The function creates a new directory for output if not specified.
+        - Annotation results are saved as text files with the same names as the input images.
+        - Each line in the output text file represents a detected object with its class ID and segmentation points.
     """
     det_model = YOLO(det_model)
     sam_model = SAM(sam_model)
@@ -32,7 +52,9 @@ def auto_annotate(data, det_model="yolov8x.pt", sam_model="sam_b.pt", device="",
         output_dir = data.parent / f"{data.stem}_auto_annotate_labels"
     Path(output_dir).mkdir(exist_ok=True, parents=True)
 
-    det_results = det_model(data, stream=True, device=device)
+    det_results = det_model(
+        data, stream=True, device=device, conf=conf, iou=iou, imgsz=imgsz, max_det=max_det, classes=classes
+    )
 
     for result in det_results:
         class_ids = result.boxes.cls.int().tolist()  # noqa