dgenerate-ultralytics-headless 8.3.214__py3-none-any.whl → 8.4.7__py3-none-any.whl

ultralytics/cfg/datasets/TT100K.yaml

@@ -0,0 +1,346 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Tsinghua-Tencent 100K (TT100K) dataset https://cg.cs.tsinghua.edu.cn/traffic-sign/ by Tsinghua University
+# Documentation: https://cg.cs.tsinghua.edu.cn/traffic-sign/tutorial.html
+# Paper: Traffic-Sign Detection and Classification in the Wild (CVPR 2016)
+# License: CC BY-NC 2.0 license for non-commercial use only
+# Example usage: yolo train data=TT100K.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── TT100K ← downloads here (~18 GB)
+
+# 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: TT100K # dataset root dir
+train: images/train # train images (relative to 'path') 6105 images
+val: images/val # val images (relative to 'path') 7641 images (original 'other' split)
+test: images/test # test images (relative to 'path') 3071 images
+
+# Classes (221 traffic sign categories, 45 with sufficient training instances)
+names:
+  0: pl5
+  1: pl10
+  2: pl15
+  3: pl20
+  4: pl25
+  5: pl30
+  6: pl40
+  7: pl50
+  8: pl60
+  9: pl70
+  10: pl80
+  11: pl90
+  12: pl100
+  13: pl110
+  14: pl120
+  15: pm5
+  16: pm10
+  17: pm13
+  18: pm15
+  19: pm20
+  20: pm25
+  21: pm30
+  22: pm35
+  23: pm40
+  24: pm46
+  25: pm50
+  26: pm55
+  27: pm8
+  28: pn
+  29: pne
+  30: ph4
+  31: ph4.5
+  32: ph5
+  33: ps
+  34: pg
+  35: ph1.5
+  36: ph2
+  37: ph2.1
+  38: ph2.2
+  39: ph2.4
+  40: ph2.5
+  41: ph2.8
+  42: ph2.9
+  43: ph3
+  44: ph3.2
+  45: ph3.5
+  46: ph3.8
+  47: ph4.2
+  48: ph4.3
+  49: ph4.8
+  50: ph5.3
+  51: ph5.5
+  52: pb
+  53: pr10
+  54: pr100
+  55: pr20
+  56: pr30
+  57: pr40
+  58: pr45
+  59: pr50
+  60: pr60
+  61: pr70
+  62: pr80
+  63: pr90
+  64: p1
+  65: p2
+  66: p3
+  67: p4
+  68: p5
+  69: p6
+  70: p7
+  71: p8
+  72: p9
+  73: p10
+  74: p11
+  75: p12
+  76: p13
+  77: p14
+  78: p15
+  79: p16
+  80: p17
+  81: p18
+  82: p19
+  83: p20
+  84: p21
+  85: p22
+  86: p23
+  87: p24
+  88: p25
+  89: p26
+  90: p27
+  91: p28
+  92: pa8
+  93: pa10
+  94: pa12
+  95: pa13
+  96: pa14
+  97: pb5
+  98: pc
+  99: pg
+  100: ph1
+  101: ph1.3
+  102: ph1.5
+  103: ph2
+  104: ph3
+  105: ph4
+  106: ph5
+  107: pi
+  108: pl0
+  109: pl4
+  110: pl5
+  111: pl8
+  112: pl10
+  113: pl15
+  114: pl20
+  115: pl25
+  116: pl30
+  117: pl35
+  118: pl40
+  119: pl50
+  120: pl60
+  121: pl65
+  122: pl70
+  123: pl80
+  124: pl90
+  125: pl100
+  126: pl110
+  127: pl120
+  128: pm2
+  129: pm8
+  130: pm10
+  131: pm13
+  132: pm15
+  133: pm20
+  134: pm25
+  135: pm30
+  136: pm35
+  137: pm40
+  138: pm46
+  139: pm50
+  140: pm55
+  141: pn
+  142: pne
+  143: po
+  144: pr10
+  145: pr100
+  146: pr20
+  147: pr30
+  148: pr40
+  149: pr45
+  150: pr50
+  151: pr60
+  152: pr70
+  153: pr80
+  154: ps
+  155: w1
+  156: w2
+  157: w3
+  158: w5
+  159: w8
+  160: w10
+  161: w12
+  162: w13
+  163: w16
+  164: w18
+  165: w20
+  166: w21
+  167: w22
+  168: w24
+  169: w28
+  170: w30
+  171: w31
+  172: w32
+  173: w34
+  174: w35
+  175: w37
+  176: w38
+  177: w41
+  178: w42
+  179: w43
+  180: w44
+  181: w45
+  182: w46
+  183: w47
+  184: w48
+  185: w49
+  186: w50
+  187: w51
+  188: w52
+  189: w53
+  190: w54
+  191: w55
+  192: w56
+  193: w57
+  194: w58
+  195: w59
+  196: w60
+  197: w62
+  198: w63
+  199: w66
+  200: i1
+  201: i2
+  202: i3
+  203: i4
+  204: i5
+  205: i6
+  206: i7
+  207: i8
+  208: i9
+  209: i10
+  210: i11
+  211: i12
+  212: i13
+  213: i14
+  214: i15
+  215: il60
+  216: il80
+  217: il100
+  218: il110
+  219: io
+  220: ip
+
+# Download script/URL (optional) ---------------------------------------------------------------------------------------
+download: |
+  import json
+  import shutil
+  from pathlib import Path
+
+  from PIL import Image
+
+  from ultralytics.utils import TQDM
+  from ultralytics.utils.downloads import download
+
+
+  def tt100k2yolo(dir):
+      """Convert TT100K annotations to YOLO format with images/{split} and labels/{split} structure."""
+      data_dir = dir / "data"
+      anno_file = data_dir / "annotations.json"
+
+      print("Loading annotations...")
+      with open(anno_file, encoding="utf-8") as f:
+          data = json.load(f)
+
+      # Build class name to index mapping from yaml
+      names = yaml["names"]
+      class_to_idx = {v: k for k, v in names.items()}
+
+      # Create directories
+      for split in ["train", "val", "test"]:
+          (dir / "images" / split).mkdir(parents=True, exist_ok=True)
+          (dir / "labels" / split).mkdir(parents=True, exist_ok=True)
+
+      print("Converting annotations to YOLO format...")
+      skipped = 0
+      for img_id, img_data in TQDM(data["imgs"].items(), desc="Processing"):
+          img_path_str = img_data["path"]
+          if "train" in img_path_str:
+              split = "train"
+          elif "test" in img_path_str:
+              split = "test"
+          else:
+              split = "val"
+
+          # Source and destination paths
+          src_img = data_dir / img_path_str
+          if not src_img.exists():
+              continue
+
+          dst_img = dir / "images" / split / src_img.name
+
+          # Get image dimensions
+          try:
+              with Image.open(src_img) as img:
+                  img_width, img_height = img.size
+          except Exception as e:
+              print(f"Error reading {src_img}: {e}")
+              continue
+
+          # Copy image to destination
+          shutil.copy2(src_img, dst_img)
+
+          # Convert annotations
+          label_file = dir / "labels" / split / f"{src_img.stem}.txt"
+          lines = []
+
+          for obj in img_data.get("objects", []):
+              category = obj["category"]
+              if category not in class_to_idx:
+                  skipped += 1
+                  continue
+
+              bbox = obj["bbox"]
+              xmin, ymin = bbox["xmin"], bbox["ymin"]
+              xmax, ymax = bbox["xmax"], bbox["ymax"]
+
+              # Convert to YOLO format (normalized center coordinates and dimensions)
+              x_center = ((xmin + xmax) / 2.0) / img_width
+              y_center = ((ymin + ymax) / 2.0) / img_height
+              width = (xmax - xmin) / img_width
+              height = (ymax - ymin) / img_height
+
+              # Clip to valid range
+              x_center = max(0, min(1, x_center))
+              y_center = max(0, min(1, y_center))
+              width = max(0, min(1, width))
+              height = max(0, min(1, height))
+
+              cls_idx = class_to_idx[category]
+              lines.append(f"{cls_idx} {x_center:.6f} {y_center:.6f} {width:.6f} {height:.6f}\n")
+
+          # Write label file
+          if lines:
+              label_file.write_text("".join(lines), encoding="utf-8")
+
+      if skipped:
+          print(f"Skipped {skipped} annotations with unknown categories")
+      print("Conversion complete!")
+
+
+  # Download
+  dir = Path(yaml["path"])  # dataset root dir
+  urls = ["https://cg.cs.tsinghua.edu.cn/traffic-sign/data_model_code/data.zip"]
+  download(urls, dir=dir, curl=True, threads=1)
+
+  # Convert
+  tt100k2yolo(dir)

ultralytics/cfg/datasets/VOC.yaml

@@ -1,7 +1,7 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 # PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC by University of Oxford
-# Documentation: # Documentation: https://docs.ultralytics.com/datasets/detect/voc/
+# Documentation: https://docs.ultralytics.com/datasets/detect/voc/
 # Example usage: yolo train data=VOC.yaml
 # parent
 # ├── ultralytics
@@ -59,22 +59,21 @@ download: |
           x, y, w, h = (box[0] + box[1]) / 2.0 - 1, (box[2] + box[3]) / 2.0 - 1, box[1] - box[0], box[3] - box[2]
           return x * dw, y * dh, w * dw, h * dh
 
-      in_file = open(path / f"VOC{year}/Annotations/{image_id}.xml")
-      out_file = open(lb_path, "w")
-      tree = ET.parse(in_file)
-      root = tree.getroot()
-      size = root.find("size")
-      w = int(size.find("width").text)
-      h = int(size.find("height").text)
+      with open(path / f"VOC{year}/Annotations/{image_id}.xml") as in_file, open(lb_path, "w", encoding="utf-8") as out_file:
+          tree = ET.parse(in_file)
+          root = tree.getroot()
+          size = root.find("size")
+          w = int(size.find("width").text)
+          h = int(size.find("height").text)
 
-      names = list(yaml["names"].values())  # names list
-      for obj in root.iter("object"):
-          cls = obj.find("name").text
-          if cls in names and int(obj.find("difficult").text) != 1:
-              xmlbox = obj.find("bndbox")
-              bb = convert_box((w, h), [float(xmlbox.find(x).text) for x in ("xmin", "xmax", "ymin", "ymax")])
-              cls_id = names.index(cls)  # class id
-              out_file.write(" ".join(str(a) for a in (cls_id, *bb)) + "\n")
+          names = list(yaml["names"].values())  # names list
+          for obj in root.iter("object"):
+              cls = obj.find("name").text
+              if cls in names and int(obj.find("difficult").text) != 1:
+                  xmlbox = obj.find("bndbox")
+                  bb = convert_box((w, h), [float(xmlbox.find(x).text) for x in ("xmin", "xmax", "ymin", "ymax")])
+                  cls_id = names.index(cls)  # class id
+                  out_file.write(" ".join(str(a) for a in (cls_id, *bb)) + "\n")
 
 
   # Download

ultralytics/cfg/datasets/african-wildlife.yaml

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# African-wildlife dataset by Ultralytics
+# African Wildlife dataset by Ultralytics
 # Documentation: https://docs.ultralytics.com/datasets/detect/african-wildlife/
 # Example usage: yolo train data=african-wildlife.yaml
 # parent

ultralytics/cfg/datasets/coco-pose.yaml

@@ -22,6 +22,27 @@ flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]
 names:
   0: person
 
+# Keypoint names per class
+kpt_names:
+  0:
+    - nose
+    - left_eye
+    - right_eye
+    - left_ear
+    - right_ear
+    - left_shoulder
+    - right_shoulder
+    - left_elbow
+    - right_elbow
+    - left_wrist
+    - right_wrist
+    - left_hip
+    - right_hip
+    - left_knee
+    - right_knee
+    - left_ankle
+    - right_ankle
+
 # Download script/URL (optional)
 download: |
   from pathlib import Path

ultralytics/cfg/datasets/coco12-formats.yaml

@@ -0,0 +1,101 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# COCO12-Formats dataset (12 images testing all supported image formats) by Ultralytics
+# Documentation: https://docs.ultralytics.com/datasets/detect/coco12-formats/
+# Example usage: yolo train data=coco12-formats.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── coco12-formats ← downloads here (1 MB)
+
+# 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: coco12-formats # dataset root dir
+train: images/train # train images (relative to 'path') 6 images
+val: images/val # val images (relative to 'path') 6 images
+test: # test images (optional)
+
+# Classes
+names:
+  0: person
+  1: bicycle
+  2: car
+  3: motorcycle
+  4: airplane
+  5: bus
+  6: train
+  7: truck
+  8: boat
+  9: traffic light
+  10: fire hydrant
+  11: stop sign
+  12: parking meter
+  13: bench
+  14: bird
+  15: cat
+  16: dog
+  17: horse
+  18: sheep
+  19: cow
+  20: elephant
+  21: bear
+  22: zebra
+  23: giraffe
+  24: backpack
+  25: umbrella
+  26: handbag
+  27: tie
+  28: suitcase
+  29: frisbee
+  30: skis
+  31: snowboard
+  32: sports ball
+  33: kite
+  34: baseball bat
+  35: baseball glove
+  36: skateboard
+  37: surfboard
+  38: tennis racket
+  39: bottle
+  40: wine glass
+  41: cup
+  42: fork
+  43: knife
+  44: spoon
+  45: bowl
+  46: banana
+  47: apple
+  48: sandwich
+  49: orange
+  50: broccoli
+  51: carrot
+  52: hot dog
+  53: pizza
+  54: donut
+  55: cake
+  56: chair
+  57: couch
+  58: potted plant
+  59: bed
+  60: dining table
+  61: toilet
+  62: tv
+  63: laptop
+  64: mouse
+  65: remote
+  66: keyboard
+  67: cell phone
+  68: microwave
+  69: oven
+  70: toaster
+  71: sink
+  72: refrigerator
+  73: book
+  74: clock
+  75: vase
+  76: scissors
+  77: teddy bear
+  78: hair drier
+  79: toothbrush
+
+# Download script/URL (optional)
+download: https://github.com/ultralytics/assets/releases/download/v0.0.0/coco12-formats.zip

ultralytics/cfg/datasets/coco128-seg.yaml

@@ -2,7 +2,7 @@
 
 # COCO128-seg dataset https://www.kaggle.com/datasets/ultralytics/coco128 (first 128 images from COCO train2017) by Ultralytics
 # Documentation: https://docs.ultralytics.com/datasets/segment/coco/
-# Example usage: yolo train data=coco128.yaml
+# Example usage: yolo train data=coco128-seg.yaml
 # parent
 # ├── ultralytics
 # └── datasets

ultralytics/cfg/datasets/coco8-pose.yaml

@@ -22,5 +22,26 @@ flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]
 names:
   0: person
 
+# Keypoint names per class
+kpt_names:
+  0:
+    - nose
+    - left_eye
+    - right_eye
+    - left_ear
+    - right_ear
+    - left_shoulder
+    - right_shoulder
+    - left_elbow
+    - right_elbow
+    - left_wrist
+    - right_wrist
+    - left_hip
+    - right_hip
+    - left_knee
+    - right_knee
+    - left_ankle
+    - right_ankle
+
 # Download script/URL (optional)
 download: https://github.com/ultralytics/assets/releases/download/v0.0.0/coco8-pose.zip

ultralytics/cfg/datasets/dog-pose.yaml

@@ -20,5 +20,33 @@ kpt_shape: [24, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y
 names:
   0: dog
 
+# Keypoint names per class
+kpt_names:
+  0:
+    - front_left_paw
+    - front_left_knee
+    - front_left_elbow
+    - rear_left_paw
+    - rear_left_knee
+    - rear_left_elbow
+    - front_right_paw
+    - front_right_knee
+    - front_right_elbow
+    - rear_right_paw
+    - rear_right_knee
+    - rear_right_elbow
+    - tail_start
+    - tail_end
+    - left_ear_base
+    - right_ear_base
+    - nose
+    - chin
+    - left_ear_tip
+    - right_ear_tip
+    - left_eye
+    - right_eye
+    - withers
+    - throat
+
 # Download script/URL (optional)
 download: https://github.com/ultralytics/assets/releases/download/v0.0.0/dog-pose.zip

ultralytics/cfg/datasets/dota8-multispectral.yaml

@@ -6,7 +6,7 @@
 # parent
 # ├── ultralytics
 # └── datasets
-#     └── dota8-multispectral ← downloads here (37.3MB)
+#     └── dota8-multispectral ← downloads here (37.3 MB)
 
 # 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: dota8-multispectral # dataset root dir

ultralytics/cfg/datasets/dota8.yaml

@@ -1,12 +1,12 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# DOTA8 dataset 8 images from split DOTAv1 dataset by Ultralytics
+# DOTA8 dataset (8 images from the DOTAv1 split) by Ultralytics
 # Documentation: https://docs.ultralytics.com/datasets/obb/dota8/
 # Example usage: yolo train model=yolov8n-obb.pt data=dota8.yaml
 # parent
 # ├── ultralytics
 # └── datasets
-#     └── dota8 ← downloads here (1MB)
+#     └── dota8 ← downloads here (1 MB)
 
 # 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: dota8 # dataset root dir

ultralytics/cfg/datasets/hand-keypoints.yaml

@@ -15,12 +15,36 @@ val: images/val # val images (relative to 'path') 7992 images
 
 # Keypoints
 kpt_shape: [21, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
-flip_idx:
-  [0, 1, 2, 4, 3, 10, 11, 12, 13, 14, 5, 6, 7, 8, 9, 15, 16, 17, 18, 19, 20]
+flip_idx: [0, 1, 2, 4, 3, 10, 11, 12, 13, 14, 5, 6, 7, 8, 9, 15, 16, 17, 18, 19, 20]
 
 # Classes
 names:
   0: hand
 
+# Keypoint names per class
+kpt_names:
+  0:
+    - wrist
+    - thumb_cmc
+    - thumb_mcp
+    - thumb_ip
+    - thumb_tip
+    - index_mcp
+    - index_pip
+    - index_dip
+    - index_tip
+    - middle_mcp
+    - middle_pip
+    - middle_dip
+    - middle_tip
+    - ring_mcp
+    - ring_pip
+    - ring_dip
+    - ring_tip
+    - pinky_mcp
+    - pinky_pip
+    - pinky_dip
+    - pinky_tip
+
 # Download script/URL (optional)
 download: https://github.com/ultralytics/assets/releases/download/v0.0.0/hand-keypoints.zip

ultralytics/cfg/datasets/kitti.yaml

@@ -0,0 +1,27 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# KITTI dataset by Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago
+# Documentation: https://docs.ultralytics.com/datasets/detect/kitti/
+# Example usage: yolo train data=kitti.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── kitti ← downloads here (390.5 MB)
+
+# 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: kitti # dataset root dir
+train: images/train # train images (relative to 'path') 5985 images
+val: images/val # val images (relative to 'path') 1496 images
+
+names:
+  0: car
+  1: van
+  2: truck
+  3: pedestrian
+  4: person_sitting
+  5: cyclist
+  6: tram
+  7: misc
+
+# Download script/URL (optional)
+download: https://github.com/ultralytics/assets/releases/download/v0.0.0/kitti.zip