ultralytics/datasets/GlobalWheat2020.yaml

# Ultralytics YOLO 🚀, AGPL-3.0 license
# Global Wheat 2020 dataset http://www.global-wheat.com/ by University of Saskatchewan
# Example usage: yolo train data=GlobalWheat2020.yaml
# parent
# ├── ultralytics
# └── datasets
#     └── GlobalWheat2020  ← downloads here (7.0 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: ../datasets/GlobalWheat2020  # dataset root dir
train: # train images (relative to 'path') 3422 images
  - images/arvalis_1
  - images/arvalis_2
  - images/arvalis_3
  - images/ethz_1
  - images/rres_1
  - images/inrae_1
  - images/usask_1
val: # val images (relative to 'path') 748 images (WARNING: train set contains ethz_1)
  - images/ethz_1
test: # test images (optional) 1276 images
  - images/utokyo_1
  - images/utokyo_2
  - images/nau_1
  - images/uq_1

# Classes
names:
  0: wheat_head


# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
  from ultralytics.yolo.utils.downloads import download
  from pathlib import Path

  # Download
  dir = Path(yaml['path'])  # dataset root dir
  urls = ['https://zenodo.org/record/4298502/files/global-wheat-codalab-official.zip',
          'https://github.com/ultralytics/yolov5/releases/download/v1.0/GlobalWheat2020_labels.zip']
  download(urls, dir=dir)

  # Make Directories
  for p in 'annotations', 'images', 'labels':
      (dir / p).mkdir(parents=True, exist_ok=True)

  # Move
  for p in 'arvalis_1', 'arvalis_2', 'arvalis_3', 'ethz_1', 'rres_1', 'inrae_1', 'usask_1', \
           'utokyo_1', 'utokyo_2', 'nau_1', 'uq_1':
      (dir / 'global-wheat-codalab-official' / p).rename(dir / 'images' / p)  # move to /images
      f = (dir / 'global-wheat-codalab-official' / p).with_suffix('.json')  # json file
      if f.exists():
          f.rename((dir / 'annotations' / p).with_suffix('.json'))  # move to /annotations