dgenerate-ultralytics-headless 8.3.214__py3-none-any.whl → 8.3.248__py3-none-any.whl

ultralytics/cfg/datasets/lvis.yaml

@@ -35,7 +35,7 @@ names:
   17: armband
   18: armchair
   19: armoire
-  20: armor/armour
+  20: armor
   21: artichoke
   22: trash can/garbage can/wastebin/dustbin/trash barrel/trash bin
   23: ashtray
@@ -245,7 +245,7 @@ names:
   227: CD player
   228: celery
   229: cellular telephone/cellular phone/cellphone/mobile phone/smart phone
-  230: chain mail/ring mail/chain armor/chain armour/ring armor/ring armour
+  230: chain mail/ring mail/chain armor/ring armor
   231: chair
   232: chaise longue/chaise/daybed
   233: chalice
@@ -305,7 +305,7 @@ names:
   287: coin
   288: colander/cullender
   289: coleslaw/slaw
-  290: coloring material/colouring material
+  290: coloring material
   291: combination lock
   292: pacifier/teething ring
   293: comic book
@@ -401,7 +401,7 @@ names:
   383: domestic ass/donkey
   384: doorknob/doorhandle
   385: doormat/welcome mat
-  386: doughnut/donut
+  386: donut
   387: dove
   388: dragonfly
   389: drawer
@@ -1072,7 +1072,7 @@ names:
   1054: tag
   1055: taillight/rear light
   1056: tambourine
-  1057: army tank/armored combat vehicle/armoured combat vehicle
+  1057: army tank/armored combat vehicle
   1058: tank/tank storage vessel/storage tank
   1059: tank top/tank top clothing
   1060: tape/tape sticky cloth or paper

ultralytics/cfg/datasets/open-images-v7.yaml

@@ -182,7 +182,7 @@ names:
   163: Dolphin
   164: Door
   165: Door handle
-  166: Doughnut
+  166: Donut
   167: Dragonfly
   168: Drawer
   169: Dress

ultralytics/cfg/datasets/tiger-pose.yaml

@@ -21,5 +21,21 @@ flip_idx: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
 names:
   0: tiger
 
+# Keypoint names per class
+kpt_names:
+  0:
+    - nose
+    - head
+    - withers
+    - tail_base
+    - right_hind_hock
+    - right_hind_paw
+    - left_hind_paw
+    - left_hind_hock
+    - right_front_wrist
+    - right_front_paw
+    - left_front_wrist
+    - left_front_paw
+
 # Download script/URL (optional)
 download: https://github.com/ultralytics/assets/releases/download/v0.0.0/tiger-pose.zip

ultralytics/cfg/datasets/xView.yaml

@@ -1,7 +1,7 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# DIUx xView 2018 Challenge https://challenge.xviewdataset.org by U.S. National Geospatial-Intelligence Agency (NGA)
-# --------  DOWNLOAD DATA MANUALLY and jar xf val_images.zip to 'datasets/xView' before running train command!  --------
+# DIUx xView 2018 Challenge dataset https://challenge.xviewdataset.org by U.S. National Geospatial-Intelligence Agency (NGA)
+# --------  Download and extract data manually to `datasets/xView` before running the train command.  --------
 # Documentation: https://docs.ultralytics.com/datasets/detect/xview/
 # Example usage: yolo train data=xView.yaml
 # parent
@@ -12,7 +12,7 @@
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
 path: xView # dataset root dir
 train: images/autosplit_train.txt # train images (relative to 'path') 90% of 847 train images
-val: images/autosplit_val.txt # train images (relative to 'path') 10% of 847 train images
+val: images/autosplit_val.txt # val images (relative to 'path') 10% of 847 train images
 
 # Classes
 names:
@@ -80,8 +80,8 @@ names:
 # Download script/URL (optional) ---------------------------------------------------------------------------------------
 download: |
   import json
-  import os
   from pathlib import Path
+  import shutil
 
   import numpy as np
   from PIL import Image
@@ -92,15 +92,15 @@ download: |
 
 
   def convert_labels(fname=Path("xView/xView_train.geojson")):
-      """Converts xView geoJSON labels to YOLO format, mapping classes to indices 0-59 and saving as text files."""
+      """Convert xView GeoJSON labels to YOLO format (classes 0-59) and save them as text files."""
       path = fname.parent
       with open(fname, encoding="utf-8") as f:
           print(f"Loading {fname}...")
           data = json.load(f)
 
       # Make dirs
-      labels = Path(path / "labels" / "train")
-      os.system(f"rm -rf {labels}")
+      labels = path / "labels" / "train"
+      shutil.rmtree(labels, ignore_errors=True)
       labels.mkdir(parents=True, exist_ok=True)
 
       # xView classes 11-94 to 0-59
@@ -113,24 +113,24 @@ download: |
       for feature in TQDM(data["features"], desc=f"Converting {fname}"):
           p = feature["properties"]
           if p["bounds_imcoords"]:
-              id = p["image_id"]
-              file = path / "train_images" / id
-              if file.exists():  # 1395.tif missing
+              image_id = p["image_id"]
+              image_file = path / "train_images" / image_id
+              if image_file.exists():  # 1395.tif missing
                   try:
                       box = np.array([int(num) for num in p["bounds_imcoords"].split(",")])
                       assert box.shape[0] == 4, f"incorrect box shape {box.shape[0]}"
                       cls = p["type_id"]
-                      cls = xview_class2index[int(cls)]  # xView class to 0-60
+                      cls = xview_class2index[int(cls)]  # xView class to 0-59
                       assert 59 >= cls >= 0, f"incorrect class index {cls}"
 
                       # Write YOLO label
-                      if id not in shapes:
-                          shapes[id] = Image.open(file).size
-                      box = xyxy2xywhn(box[None].astype(np.float), w=shapes[id][0], h=shapes[id][1], clip=True)
-                      with open((labels / id).with_suffix(".txt"), "a", encoding="utf-8") as f:
+                      if image_id not in shapes:
+                          shapes[image_id] = Image.open(image_file).size
+                      box = xyxy2xywhn(box[None].astype(float), w=shapes[image_id][0], h=shapes[image_id][1], clip=True)
+                      with open((labels / image_id).with_suffix(".txt"), "a", encoding="utf-8") as f:
                           f.write(f"{cls} {' '.join(f'{x:.6f}' for x in box[0])}\n")  # write label.txt
                   except Exception as e:
-                      print(f"WARNING: skipping one label for {file}: {e}")
+                      print(f"WARNING: skipping one label for {image_file}: {e}")
 
 
   # Download manually from https://challenge.xviewdataset.org

ultralytics/cfg/default.yaml

@@ -80,7 +80,7 @@ show_boxes: True # (bool) draw bounding boxes on images
 line_width: # (int, optional) line width of boxes; auto-scales with image size if not set
 
 # Export settings ------------------------------------------------------------------------------------------------------
-format: torchscript # (str) target format, e.g. torchscript|onnx|openvino|engine|coreml|saved_model|pb|tflite|edgetpu|tfjs|paddle|mnn|ncnn|imx|rknn
+format: torchscript # (str) target format, e.g. torchscript|onnx|openvino|engine|coreml|saved_model|pb|tflite|edgetpu|tfjs|paddle|mnn|ncnn|imx|rknn|executorch
 keras: False # (bool) TF SavedModel only (format=saved_model); enable Keras layers during export
 optimize: False # (bool) TorchScript only; apply mobile optimizations to the scripted model
 int8: False # (bool) INT8/PTQ where supported (openvino, tflite, tfjs, engine, imx); needs calibration data/fraction

ultralytics/cfg/models/11/yolo11-pose.yaml

@@ -7,7 +7,7 @@
 # Parameters
 nc: 80 # number of classes
 kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
-scales: # model compound scaling constants, i.e. 'model=yolo11n-pose.yaml' will call yolo11.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolo11n-pose.yaml' will call yolo11-pose.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.50, 0.25, 1024] # summary: 196 layers, 2908507 parameters, 2908491 gradients, 7.7 GFLOPs
   s: [0.50, 0.50, 1024] # summary: 196 layers, 9948811 parameters, 9948795 gradients, 23.5 GFLOPs

ultralytics/cfg/models/11/yoloe-11-seg.yaml

@@ -1,10 +1,10 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# YOLO11-seg instance segmentation model. For Usage examples see https://docs.ultralytics.com/tasks/segment
+# Ultralytics YOLOE-11-seg instance segmentation model. For usage examples, see https://docs.ultralytics.com/tasks/segment
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolo11n-seg.yaml' will call yolo11-seg.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yoloe-11n-seg.yaml' will call yoloe-11-seg.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.50, 0.25, 1024] # summary: 355 layers, 2876848 parameters, 2876832 gradients, 10.5 GFLOPs
   s: [0.50, 0.50, 1024] # summary: 355 layers, 10113248 parameters, 10113232 gradients, 35.8 GFLOPs

ultralytics/cfg/models/11/yoloe-11.yaml

@@ -1,10 +1,10 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# YOLO11 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
+# Ultralytics YOLOE-11 object detection model with P3/8 - P5/32 outputs. For usage examples, see https://docs.ultralytics.com/tasks/detect
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolo11n.yaml' will call yolo11.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yoloe-11n.yaml' will call yoloe-11.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
   s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs

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]
 

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]
 

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]
 

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]
 

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

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

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

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

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

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

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
 

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]

ultralytics/cfg/models/v8/yoloe-v8-seg.yaml

@@ -1,14 +1,17 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+# Ultralytics YOLOE-v8-seg instance segmentation model with P3/8 - P5/32 outputs
+# Task docs: https://docs.ultralytics.com/tasks/segment
+
 # 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=yoloe-v8n-seg.yaml' will call yoloe-v8-seg.yaml with scale 'n'
   # [depth, width, max_channels]
-  n: [0.33, 0.25, 1024] # YOLOv8n-world summary: 161 layers, 4204111 parameters, 4204095 gradients, 39.6 GFLOPs
-  s: [0.33, 0.50, 1024] # YOLOv8s-world summary: 161 layers, 13383496 parameters, 13383480 gradients, 71.5 GFLOPs
-  m: [0.67, 0.75, 768] # YOLOv8m-world summary: 201 layers, 29065310 parameters, 29065294 gradients, 131.4 GFLOPs
-  l: [1.00, 1.00, 512] # YOLOv8l-world summary: 241 layers, 47553970 parameters, 47553954 gradients, 225.6 GFLOPs
-  x: [1.00, 1.25, 512] # YOLOv8x-world summary: 241 layers, 73690217 parameters, 73690201 gradients, 330.8 GFLOPs
+  n: [0.33, 0.25, 1024] # YOLOE-v8n-seg summary: 161 layers, 4204111 parameters, 4204095 gradients, 39.6 GFLOPs
+  s: [0.33, 0.50, 1024] # YOLOE-v8s-seg summary: 161 layers, 13383496 parameters, 13383480 gradients, 71.5 GFLOPs
+  m: [0.67, 0.75, 768] # YOLOE-v8m-seg summary: 201 layers, 29065310 parameters, 29065294 gradients, 131.4 GFLOPs
+  l: [1.00, 1.00, 512] # YOLOE-v8l-seg summary: 241 layers, 47553970 parameters, 47553954 gradients, 225.6 GFLOPs
+  x: [1.00, 1.25, 512] # YOLOE-v8x-seg summary: 241 layers, 73690217 parameters, 73690201 gradients, 330.8 GFLOPs
 
 # YOLOv8.0n backbone
 backbone:

ultralytics/cfg/models/v8/yoloe-v8.yaml

@@ -1,14 +1,17 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+# Ultralytics YOLOE-v8 object detection model with P3/8 - P5/32 outputs
+# Task docs: https://docs.ultralytics.com/tasks/detect
+
 # 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=yoloe-v8n.yaml' will call yoloe-v8.yaml with scale 'n'
   # [depth, width, max_channels]
-  n: [0.33, 0.25, 1024] # YOLOv8n-worldv2 summary: 148 layers, 3695183 parameters, 3695167 gradients, 19.5 GFLOPS
-  s: [0.33, 0.50, 1024] # YOLOv8s-worldv2 summary: 148 layers, 12759880 parameters, 12759864 gradients, 51.0 GFLOPS
-  m: [0.67, 0.75, 768] # YOLOv8m-worldv2 summary: 188 layers, 28376158 parameters, 28376142 gradients, 110.5 GFLOPS
-  l: [1.00, 1.00, 512] # YOLOv8l-worldv2 summary: 228 layers, 46832050 parameters, 46832034 gradients, 204.5 GFLOPS
-  x: [1.00, 1.25, 512] # YOLOv8x-worldv2 summary: 228 layers, 72886377 parameters, 72886361 gradients, 309.3 GFLOPS
+  n: [0.33, 0.25, 1024] # YOLOE-v8n summary: 148 layers, 3695183 parameters, 3695167 gradients, 19.5 GFLOPs
+  s: [0.33, 0.50, 1024] # YOLOE-v8s summary: 148 layers, 12759880 parameters, 12759864 gradients, 51.0 GFLOPs
+  m: [0.67, 0.75, 768] # YOLOE-v8m summary: 188 layers, 28376158 parameters, 28376142 gradients, 110.5 GFLOPs
+  l: [1.00, 1.00, 512] # YOLOE-v8l summary: 228 layers, 46832050 parameters, 46832034 gradients, 204.5 GFLOPs
+  x: [1.00, 1.25, 512] # YOLOE-v8x summary: 228 layers, 72886377 parameters, 72886361 gradients, 309.3 GFLOPs
 
 # YOLOv8.0n backbone
 backbone:

ultralytics/cfg/models/v8/yolov8-cls-resnet101.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 1000 # 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=yolov8n-cls-resnet101.yaml' will call yolov8-cls-resnet101.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.33, 0.25, 1024]
   s: [0.33, 0.50, 1024]

ultralytics/cfg/models/v8/yolov8-cls-resnet50.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 1000 # 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=yolov8n-cls-resnet50.yaml' will call yolov8-cls-resnet50.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.33, 0.25, 1024]
   s: [0.33, 0.50, 1024]

ultralytics/cfg/models/v8/yolov8-ghost-p2.yaml

@@ -1,13 +1,13 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# Ultralytics YOLOv8 object detection model with P2/4 - P5/32 outputs
+# Ultralytics YOLOv8-ghost object detection model with P2/4 - P5/32 outputs
 # Model docs: https://docs.ultralytics.com/models/yolov8
 # Task docs: https://docs.ultralytics.com/tasks/detect
 # Employs Ghost convolutions and modules proposed in Huawei's GhostNet in https://arxiv.org/abs/1911.11907v2
 
 # 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=yolov8n-ghost-p2.yaml' will call yolov8-ghost-p2.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.33, 0.25, 1024] # YOLOv8n-ghost-p2 summary: 290 layers, 2033944 parameters, 2033928 gradients, 13.8 GFLOPs
   s: [0.33, 0.50, 1024] # YOLOv8s-ghost-p2 summary: 290 layers, 5562080 parameters, 5562064 gradients, 25.1 GFLOPs

ultralytics/cfg/models/v8/yolov8-ghost-p6.yaml

@@ -1,13 +1,13 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# Ultralytics YOLOv8 object detection model with P3/8 - P6/64 outputs
+# Ultralytics YOLOv8-ghost object detection model with P3/8 - P6/64 outputs
 # Model docs: https://docs.ultralytics.com/models/yolov8
 # Task docs: https://docs.ultralytics.com/tasks/detect
 # Employs Ghost convolutions and modules proposed in Huawei's GhostNet in https://arxiv.org/abs/1911.11907v2
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n-p6.yaml' will call yolov8-p6.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov8n-ghost-p6.yaml' will call yolov8-ghost-p6.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.33, 0.25, 1024] # YOLOv8n-ghost-p6 summary: 312 layers, 2901100 parameters, 2901084 gradients, 5.8 GFLOPs
   s: [0.33, 0.50, 1024] # YOLOv8s-ghost-p6 summary: 312 layers, 9520008 parameters, 9519992 gradients, 16.4 GFLOPs

ultralytics/cfg/models/v8/yolov8-ghost.yaml

@@ -1,13 +1,13 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# Ultralytics YOLOv8 object detection model with P3/8 - P5/32 outputs
+# Ultralytics YOLOv8-ghost object detection model with P3/8 - P5/32 outputs
 # Model docs: https://docs.ultralytics.com/models/yolov8
 # Task docs: https://docs.ultralytics.com/tasks/detect
 # Employs Ghost convolutions and modules proposed in Huawei's GhostNet in https://arxiv.org/abs/1911.11907v2
 
 # 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=yolov8n-ghost.yaml' will call yolov8-ghost.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.33, 0.25, 1024] # YOLOv8n-ghost summary: 237 layers, 1865316 parameters, 1865300 gradients, 5.8 GFLOPs
   s: [0.33, 0.50, 1024] # YOLOv8s-ghost summary: 237 layers, 5960072 parameters, 5960056 gradients, 16.4 GFLOPs

ultralytics/cfg/models/v8/yolov8-obb.yaml

@@ -6,7 +6,7 @@
 
 # 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=yolov8n-obb.yaml' will call yolov8-obb.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.33, 0.25, 1024] # YOLOv8n-obb summary: 144 layers, 3228867 parameters, 3228851 gradients, 9.1 GFLOPs
   s: [0.33, 0.50, 1024] # YOLOv8s-obb summary: 144 layers, 11452739 parameters, 11452723 gradients, 29.8 GFLOPs

ultralytics/cfg/models/v8/yolov8-p2.yaml

@@ -6,7 +6,7 @@
 
 # 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=yolov8n-p2.yaml' will call yolov8-p2.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.33, 0.25, 1024]
   s: [0.33, 0.50, 1024]

ultralytics/cfg/models/v8/yolov8-pose-p6.yaml

@@ -7,7 +7,7 @@
 # Parameters
 nc: 1 # number of classes
 kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
-scales: # model compound scaling constants, i.e. 'model=yolov8n-p6.yaml' will call yolov8-p6.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov8n-pose-p6.yaml' will call yolov8-pose-p6.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.33, 0.25, 1024]
   s: [0.33, 0.50, 1024]

ultralytics/cfg/models/v8/yolov8-rtdetr.yaml

@@ -6,7 +6,7 @@
 
 # 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=yolov8n-rtdetr.yaml' will call yolov8-rtdetr.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.33, 0.25, 1024] # YOLOv8n-rtdetr summary: 235 layers, 9643868 parameters, 9643868 gradients, 17.1 GFLOPs
   s: [0.33, 0.50, 1024] # YOLOv8s-rtdetr summary: 235 layers, 16518572 parameters, 16518572 gradients, 32.8 GFLOPs

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)

ultralytics/cfg/models/v8/yolov8-world.yaml

@@ -6,7 +6,7 @@
 
 # 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=yolov8n-world.yaml' will call yolov8-world.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.33, 0.25, 1024] # YOLOv8n-world summary: 161 layers, 4204111 parameters, 4204095 gradients, 39.6 GFLOPs
   s: [0.33, 0.50, 1024] # YOLOv8s-world summary: 161 layers, 13383496 parameters, 13383480 gradients, 71.5 GFLOPs

ultralytics/cfg/models/v8/yolov8-worldv2.yaml

@@ -6,13 +6,13 @@
 
 # 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=yolov8n-worldv2.yaml' will call yolov8-worldv2.yaml with scale 'n'
   # [depth, width, max_channels]
-  n: [0.33, 0.25, 1024] # YOLOv8n-worldv2 summary: 148 layers, 3695183 parameters, 3695167 gradients, 19.5 GFLOPS
-  s: [0.33, 0.50, 1024] # YOLOv8s-worldv2 summary: 148 layers, 12759880 parameters, 12759864 gradients, 51.0 GFLOPS
-  m: [0.67, 0.75, 768] # YOLOv8m-worldv2 summary: 188 layers, 28376158 parameters, 28376142 gradients, 110.5 GFLOPS
-  l: [1.00, 1.00, 512] # YOLOv8l-worldv2 summary: 228 layers, 46832050 parameters, 46832034 gradients, 204.5 GFLOPS
-  x: [1.00, 1.25, 512] # YOLOv8x-worldv2 summary: 228 layers, 72886377 parameters, 72886361 gradients, 309.3 GFLOPS
+  n: [0.33, 0.25, 1024] # YOLOv8n-worldv2 summary: 148 layers, 3695183 parameters, 3695167 gradients, 19.5 GFLOPs
+  s: [0.33, 0.50, 1024] # YOLOv8s-worldv2 summary: 148 layers, 12759880 parameters, 12759864 gradients, 51.0 GFLOPs
+  m: [0.67, 0.75, 768] # YOLOv8m-worldv2 summary: 188 layers, 28376158 parameters, 28376142 gradients, 110.5 GFLOPs
+  l: [1.00, 1.00, 512] # YOLOv8l-worldv2 summary: 228 layers, 46832050 parameters, 46832034 gradients, 204.5 GFLOPs
+  x: [1.00, 1.25, 512] # YOLOv8x-worldv2 summary: 228 layers, 72886377 parameters, 72886361 gradients, 309.3 GFLOPs
 
 # YOLOv8.0n backbone
 backbone:

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)

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

@@ -19,8 +19,7 @@ def auto_annotate(
     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 in YOLO format.
@@ -35,8 +34,8 @@ def auto_annotate(
         imgsz (int): Input image resize dimension.
         max_det (int): Maximum number of detections per image.
         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.
+        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