Argoverse 데이터셋

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

# Argoverse-HD dataset (ring-front-center camera) by Argo AI: https://www.cs.cmu.edu/~mengtial/proj/streaming/
# Documentation: https://docs.ultralytics.com/datasets/detect/argoverse/
# Example usage: yolo train data=Argoverse.yaml
# parent
# ├── ultralytics
# └── datasets
#     └── Argoverse ← downloads here (31.5 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: Argoverse # dataset root dir
train: Argoverse-1.1/images/train/ # train images (relative to 'path') 39384 images
val: Argoverse-1.1/images/val/ # val images (relative to 'path') 15062 images
test: Argoverse-1.1/images/test/ # test images (optional) https://eval.ai/web/challenges/challenge-page/800/overview

# Classes
names:
  0: person
  1: bicycle
  2: car
  3: motorcycle
  4: bus
  5: truck
  6: traffic_light
  7: stop_sign

# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
  import json
  from pathlib import Path

  from ultralytics.utils import TQDM
  from ultralytics.utils.downloads import download

  def argoverse2yolo(annotation_file):
      """Convert Argoverse dataset annotations to YOLO format for object detection tasks."""
      labels = {}
      with open(annotation_file, encoding="utf-8") as f:
          a = json.load(f)
      for annot in TQDM(a["annotations"], desc=f"Converting {annotation_file} to YOLO format..."):
          img_id = annot["image_id"]
          img_name = a["images"][img_id]["name"]
          img_label_name = f"{Path(img_name).stem}.txt"

          cls = annot["category_id"]  # instance class id
          x_center, y_center, width, height = annot["bbox"]
          x_center = (x_center + width / 2) / 1920.0  # offset and scale
          y_center = (y_center + height / 2) / 1200.0  # offset and scale
          width /= 1920.0  # scale
          height /= 1200.0  # scale

          img_dir = annotation_file.parents[2] / "Argoverse-1.1" / "labels" / a["seq_dirs"][a["images"][annot["image_id"]]["sid"]]
          if not img_dir.exists():
              img_dir.mkdir(parents=True, exist_ok=True)

          k = str(img_dir / img_label_name)
          if k not in labels:
              labels[k] = []
          labels[k].append(f"{cls} {x_center} {y_center} {width} {height}\n")

      for k in labels:
          with open(k, "w", encoding="utf-8") as f:
              f.writelines(labels[k])

  # Download 'https://argoverse-hd.s3.us-east-2.amazonaws.com/Argoverse-HD-Full.zip' (deprecated S3 link)
  dir = Path(yaml["path"])  # dataset root dir
  urls = ["https://drive.google.com/file/d/1st9qW3BeIwQsnR0t8mRpvbsSWIo16ACi/view?usp=drive_link"]
  print("\n\nWARNING: Argoverse dataset MUST be downloaded manually, autodownload will NOT work.")
  print(f"WARNING: Manually download Argoverse dataset '{urls[0]}' to '{dir}' and re-run your command.\n\n")
  # download(urls, dir=dir)

  # Convert
  annotations_dir = "Argoverse-HD/annotations/"
  (dir / "Argoverse-1.1" / "tracking").rename(dir / "Argoverse-1.1" / "images")  # rename 'tracking' to 'images'
  for d in "train.json", "val.json":
      argoverse2yolo(dir / annotations_dir / d)  # convert Argoverse annotations to YOLO labels