dgenerate-ultralytics-headless 8.3.253__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

@@ -0,0 +1,102 @@
+# 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: https://docs.ultralytics.com/datasets/detect/voc/
+# Example usage: yolo train data=VOC.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── VOC ← downloads here (2.8 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: VOC
+train: # train images (relative to 'path') 16551 images
+  - images/train2012
+  - images/train2007
+  - images/val2012
+  - images/val2007
+val: # val images (relative to 'path') 4952 images
+  - images/test2007
+test: # test images (optional)
+  - images/test2007
+
+# Classes
+names:
+  0: aeroplane
+  1: bicycle
+  2: bird
+  3: boat
+  4: bottle
+  5: bus
+  6: car
+  7: cat
+  8: chair
+  9: cow
+  10: diningtable
+  11: dog
+  12: horse
+  13: motorbike
+  14: person
+  15: pottedplant
+  16: sheep
+  17: sofa
+  18: train
+  19: tvmonitor
+
+# Download script/URL (optional) ---------------------------------------------------------------------------------------
+download: |
+  import xml.etree.ElementTree as ET
+  from pathlib import Path
+
+  from ultralytics.utils.downloads import download
+  from ultralytics.utils import ASSETS_URL, TQDM
+
+  def convert_label(path, lb_path, year, image_id):
+      """Converts XML annotations from VOC format to YOLO format by extracting bounding boxes and class IDs."""
+
+      def convert_box(size, box):
+          dw, dh = 1.0 / size[0], 1.0 / size[1]
+          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
+
+      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")
+
+
+  # Download
+  dir = Path(yaml["path"])  # dataset root dir
+  urls = [
+      f"{ASSETS_URL}/VOCtrainval_06-Nov-2007.zip",  # 446MB, 5012 images
+      f"{ASSETS_URL}/VOCtest_06-Nov-2007.zip",  # 438MB, 4953 images
+      f"{ASSETS_URL}/VOCtrainval_11-May-2012.zip",  # 1.95GB, 17126 images
+  ]
+  download(urls, dir=dir / "images", threads=3, exist_ok=True)  # download and unzip over existing (required)
+
+  # Convert
+  path = dir / "images/VOCdevkit"
+  for year, image_set in ("2012", "train"), ("2012", "val"), ("2007", "train"), ("2007", "val"), ("2007", "test"):
+      imgs_path = dir / "images" / f"{image_set}{year}"
+      lbs_path = dir / "labels" / f"{image_set}{year}"
+      imgs_path.mkdir(exist_ok=True, parents=True)
+      lbs_path.mkdir(exist_ok=True, parents=True)
+
+      with open(path / f"VOC{year}/ImageSets/Main/{image_set}.txt") as f:
+          image_ids = f.read().strip().split()
+      for id in TQDM(image_ids, desc=f"{image_set}{year}"):
+          f = path / f"VOC{year}/JPEGImages/{id}.jpg"  # old img path
+          lb_path = (lbs_path / f.name).with_suffix(".txt")  # new label path
+          f.rename(imgs_path / f.name)  # move image
+          convert_label(path, lb_path, year, id)  # convert labels to YOLO format

ultralytics/cfg/datasets/VisDrone.yaml

@@ -0,0 +1,87 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# VisDrone2019-DET dataset https://github.com/VisDrone/VisDrone-Dataset by Tianjin University
+# Documentation: https://docs.ultralytics.com/datasets/detect/visdrone/
+# Example usage: yolo train data=VisDrone.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── VisDrone ← downloads here (2.3 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: VisDrone # dataset root dir
+train: images/train # train images (relative to 'path') 6471 images
+val: images/val # val images (relative to 'path') 548 images
+test: images/test # test-dev images (optional) 1610 images
+
+# Classes
+names:
+  0: pedestrian
+  1: people
+  2: bicycle
+  3: car
+  4: van
+  5: truck
+  6: tricycle
+  7: awning-tricycle
+  8: bus
+  9: motor
+
+# Download script/URL (optional) ---------------------------------------------------------------------------------------
+download: |
+  import os
+  from pathlib import Path
+  import shutil
+
+  from ultralytics.utils.downloads import download
+  from ultralytics.utils import ASSETS_URL, TQDM
+
+
+  def visdrone2yolo(dir, split, source_name=None):
+      """Convert VisDrone annotations to YOLO format with images/{split} and labels/{split} structure."""
+      from PIL import Image
+
+      source_dir = dir / (source_name or f"VisDrone2019-DET-{split}")
+      images_dir = dir / "images" / split
+      labels_dir = dir / "labels" / split
+      labels_dir.mkdir(parents=True, exist_ok=True)
+
+      # Move images to new structure
+      if (source_images_dir := source_dir / "images").exists():
+          images_dir.mkdir(parents=True, exist_ok=True)
+          for img in source_images_dir.glob("*.jpg"):
+              img.rename(images_dir / img.name)
+
+      for f in TQDM((source_dir / "annotations").glob("*.txt"), desc=f"Converting {split}"):
+          img_size = Image.open(images_dir / f.with_suffix(".jpg").name).size
+          dw, dh = 1.0 / img_size[0], 1.0 / img_size[1]
+          lines = []
+
+          with open(f, encoding="utf-8") as file:
+              for row in [x.split(",") for x in file.read().strip().splitlines()]:
+                  if row[4] != "0":  # Skip ignored regions
+                      x, y, w, h = map(int, row[:4])
+                      cls = int(row[5]) - 1
+                      # Convert to YOLO format
+                      x_center, y_center = (x + w / 2) * dw, (y + h / 2) * dh
+                      w_norm, h_norm = w * dw, h * dh
+                      lines.append(f"{cls} {x_center:.6f} {y_center:.6f} {w_norm:.6f} {h_norm:.6f}\n")
+
+          (labels_dir / f.name).write_text("".join(lines), encoding="utf-8")
+
+
+  # Download (ignores test-challenge split)
+  dir = Path(yaml["path"])  # dataset root dir
+  urls = [
+      f"{ASSETS_URL}/VisDrone2019-DET-train.zip",
+      f"{ASSETS_URL}/VisDrone2019-DET-val.zip",
+      f"{ASSETS_URL}/VisDrone2019-DET-test-dev.zip",
+      # f"{ASSETS_URL}/VisDrone2019-DET-test-challenge.zip",
+  ]
+  download(urls, dir=dir, threads=4)
+
+  # Convert
+  splits = {"VisDrone2019-DET-train": "train", "VisDrone2019-DET-val": "val", "VisDrone2019-DET-test-dev": "test"}
+  for folder, split in splits.items():
+      visdrone2yolo(dir, split, folder)  # convert VisDrone annotations to YOLO labels
+      shutil.rmtree(dir / folder)  # cleanup original directory

ultralytics/cfg/datasets/african-wildlife.yaml

@@ -0,0 +1,25 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# African Wildlife dataset by Ultralytics
+# Documentation: https://docs.ultralytics.com/datasets/detect/african-wildlife/
+# Example usage: yolo train data=african-wildlife.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── african-wildlife ← downloads here (100 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: african-wildlife # dataset root dir
+train: images/train # train images (relative to 'path') 1052 images
+val: images/val # val images (relative to 'path') 225 images
+test: images/test # test images (relative to 'path') 227 images
+
+# Classes
+names:
+  0: buffalo
+  1: elephant
+  2: rhino
+  3: zebra
+
+# Download script/URL (optional)
+download: https://github.com/ultralytics/assets/releases/download/v0.0.0/african-wildlife.zip

ultralytics/cfg/datasets/brain-tumor.yaml

@@ -0,0 +1,22 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Brain-tumor dataset by Ultralytics
+# Documentation: https://docs.ultralytics.com/datasets/detect/brain-tumor/
+# Example usage: yolo train data=brain-tumor.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── brain-tumor ← downloads here (4.21 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: brain-tumor # dataset root dir
+train: images/train # train images (relative to 'path') 893 images
+val: images/val # val images (relative to 'path') 223 images
+
+# Classes
+names:
+  0: negative
+  1: positive
+
+# Download script/URL (optional)
+download: https://github.com/ultralytics/assets/releases/download/v0.0.0/brain-tumor.zip

ultralytics/cfg/datasets/carparts-seg.yaml

@@ -0,0 +1,44 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Carparts-seg dataset by Ultralytics
+# Documentation: https://docs.ultralytics.com/datasets/segment/carparts-seg/
+# Example usage: yolo train data=carparts-seg.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── carparts-seg ← downloads here (133 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: carparts-seg # dataset root dir
+train: images/train # train images (relative to 'path') 3516 images
+val: images/val # val images (relative to 'path') 276 images
+test: images/test # test images (relative to 'path') 401 images
+
+# Classes
+names:
+  0: back_bumper
+  1: back_door
+  2: back_glass
+  3: back_left_door
+  4: back_left_light
+  5: back_light
+  6: back_right_door
+  7: back_right_light
+  8: front_bumper
+  9: front_door
+  10: front_glass
+  11: front_left_door
+  12: front_left_light
+  13: front_light
+  14: front_right_door
+  15: front_right_light
+  16: hood
+  17: left_mirror
+  18: object
+  19: right_mirror
+  20: tailgate
+  21: trunk
+  22: wheel
+
+# Download script/URL (optional)
+download: https://github.com/ultralytics/assets/releases/download/v0.0.0/carparts-seg.zip

ultralytics/cfg/datasets/coco-pose.yaml

@@ -0,0 +1,64 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# COCO 2017 Keypoints dataset https://cocodataset.org by Microsoft
+# Documentation: https://docs.ultralytics.com/datasets/pose/coco/
+# Example usage: yolo train data=coco-pose.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── coco-pose ← downloads here (20.1 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: coco-pose # dataset root dir
+train: train2017.txt # train images (relative to 'path') 56599 images
+val: val2017.txt # val images (relative to 'path') 2346 images
+test: test-dev2017.txt # 20288 of 40670 images, submit to https://codalab.lisn.upsaclay.fr/competitions/7403
+
+# Keypoints
+kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
+flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]
+
+# Classes
+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
+
+  from ultralytics.utils import ASSETS_URL
+  from ultralytics.utils.downloads import download
+
+  # Download labels
+  dir = Path(yaml["path"])  # dataset root dir
+
+  urls = [f"{ASSETS_URL}/coco2017labels-pose.zip"]
+  download(urls, dir=dir.parent)
+  # Download data
+  urls = [
+      "http://images.cocodataset.org/zips/train2017.zip",  # 19G, 118k images
+      "http://images.cocodataset.org/zips/val2017.zip",  # 1G, 5k images
+      "http://images.cocodataset.org/zips/test2017.zip",  # 7G, 41k images (optional)
+  ]
+  download(urls, dir=dir / "images", threads=3)