مجموعة بيانات Cityscapes#

# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license

# Cityscapes semantic segmentation dataset (19 classes)
# Documentation: https://docs.ultralytics.com/datasets/semantic/cityscapes
# Example usage: yolo semantic train data=cityscapes.yaml model=yolo26n-sem.pt
# parent
# ├── ultralytics
# └── datasets
#     └── cityscapes ← downloads here (11 GB)
#         └── images
#         └── masks

# Dataset root directory
path: cityscapes # dataset root dir
train: images/train # train images (relative to 'path') 2975 images
val: images/val # val images (relative to 'path') 500 images
test: images/test # test images (relative to 'path') 1525 images

masks_dir: masks # semantic mask directory

# Cityscapes 19-class labels
names:
  0: road
  1: sidewalk
  2: building
  3: wall
  4: fence
  5: pole
  6: traffic light
  7: traffic sign
  8: vegetation
  9: terrain
  10: sky
  11: person
  12: rider
  13: car
  14: truck
  15: bus
  16: train
  17: motorcycle
  18: bicycle

# Map source label IDs to train IDs; ignore_label is converted to 255.
label_mapping:
  -1: ignore_label
  0: ignore_label
  1: ignore_label
  2: ignore_label
  3: ignore_label
  4: ignore_label
  5: ignore_label
  6: ignore_label
  7: 0
  8: 1
  9: ignore_label
  10: ignore_label
  11: 2
  12: 3
  13: 4
  14: ignore_label
  15: ignore_label
  16: ignore_label
  17: 5
  18: ignore_label
  19: 6
  20: 7
  21: 8
  22: 9
  23: 10
  24: 11
  25: 12
  26: 13
  27: 14
  28: 15
  29: ignore_label
  30: ignore_label
  31: 16
  32: 17
  33: 18

# Preparation script (requires manual Cityscapes download)
download: |
  from pathlib import Path
  from shutil import copy2

  cityscapes_dir = Path(yaml["path"])  # dataset root dir
  # Download and extract the official Cityscapes leftImg8bit and gtFine archives into cityscapes_dir first.
  leftimg8bit_dir = cityscapes_dir / "leftImg8bit"
  gtfine_dir = cityscapes_dir / "gtFine"

  for split in ("train", "val", "test"):
      print(f"Processing {split} set")
      src_image_dir = leftimg8bit_dir / split
      dst_image_dir = cityscapes_dir / "images" / split
      dst_mask_dir = cityscapes_dir / "masks" / split
      dst_image_dir.mkdir(parents=True, exist_ok=True)
      dst_mask_dir.mkdir(parents=True, exist_ok=True)

      image_paths = sorted(src_image_dir.rglob("*_leftImg8bit.png"))
      for image_path in image_paths:
          relative_path = image_path.relative_to(src_image_dir)
          mask_path = gtfine_dir / split / relative_path.parent / image_path.name.replace(
              "_leftImg8bit.png", "_gtFine_labelIds.png"
          )
          if not mask_path.exists():
              raise FileNotFoundError(f"Mask not found for {image_path}: {mask_path}")

          image_name = image_path.name.replace("_leftImg8bit", "")
          mask_name = mask_path.name.replace("_gtFine_labelIds", "")
          copy2(image_path, dst_image_dir / image_name)
          copy2(mask_path, dst_mask_dir / mask_name)