# Global Wheat 2020 dataset http://www.global-wheat.com/
# Train command: python train.py --data GlobalWheat2020.yaml
# Default dataset location is next to YOLOv5:
#   /parent_folder
#     /datasets/GlobalWheat2020
#     /yolov5


# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
train: # 3422 images
  - ../datasets/GlobalWheat2020/images/arvalis_1
  - ../datasets/GlobalWheat2020/images/arvalis_2
  - ../datasets/GlobalWheat2020/images/arvalis_3
  - ../datasets/GlobalWheat2020/images/ethz_1
  - ../datasets/GlobalWheat2020/images/rres_1
  - ../datasets/GlobalWheat2020/images/inrae_1
  - ../datasets/GlobalWheat2020/images/usask_1

val: # 748 images (WARNING: train set contains ethz_1)
  - ../datasets/GlobalWheat2020/images/ethz_1

test: # 1276
  - ../datasets/GlobalWheat2020/images/utokyo_1
  - ../datasets/GlobalWheat2020/images/utokyo_2
  - ../datasets/GlobalWheat2020/images/nau_1
  - ../datasets/GlobalWheat2020/images/uq_1

# number of classes
nc: 1

# class names
names: [ 'wheat_head' ]


# download command/URL (optional) --------------------------------------------------------------------------------------
download: |
  from utils.general import download, Path

  # Download
  dir = Path('../datasets/GlobalWheat2020')  # dataset directory
  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 / p).rename(dir / 'images' / p)  # move to /images
      f = (dir / p).with_suffix('.json')  # json file
      if f.exists():
          f.rename((dir / 'annotations' / p).with_suffix('.json'))  # move to /annotations