VisDroneデータセット#

# 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 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