data/SKU-110K.yaml

# SKU-110K retail items dataset https://github.com/eg4000/SKU110K_CVPR19
# Train command: python train.py --data SKU-110K.yaml
# Default dataset location is next to YOLOv5:
#   /parent_folder
#     /datasets/SKU-110K
#     /yolov5


# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
train: ../datasets/SKU-110K/train.txt  # 8219 images
val: ../datasets/SKU-110K/val.txt  # 588 images
test: ../datasets/SKU-110K/test.txt  # 2936 images

# number of classes
nc: 1

# class names
names: [ 'object' ]


# download command/URL (optional) --------------------------------------------------------------------------------------
download: |
  import shutil
  from tqdm import tqdm
  from utils.general import np, pd, Path, download, xyxy2xywh

  # Download
  datasets = Path('../datasets')  # download directory
  urls = ['http://trax-geometry.s3.amazonaws.com/cvpr_challenge/SKU110K_fixed.tar.gz']
  download(urls, dir=datasets, delete=False)

  # Rename directories
  dir = (datasets / 'SKU-110K')
  if dir.exists():
      shutil.rmtree(dir)
  (datasets / 'SKU110K_fixed').rename(dir)  # rename dir
  (dir / 'labels').mkdir(parents=True, exist_ok=True)  # create labels dir

  # Convert labels
  names = 'image', 'x1', 'y1', 'x2', 'y2', 'class', 'image_width', 'image_height'  # column names
  for d in 'annotations_train.csv', 'annotations_val.csv', 'annotations_test.csv':
      x = pd.read_csv(dir / 'annotations' / d, names=names).values  # annotations
      images, unique_images = x[:, 0], np.unique(x[:, 0])
      with open((dir / d).with_suffix('.txt').__str__().replace('annotations_', ''), 'w') as f:
          f.writelines(f'./images/{s}\n' for s in unique_images)
      for im in tqdm(unique_images, desc=f'Converting {dir / d}'):
          cls = 0  # single-class dataset
          with open((dir / 'labels' / im).with_suffix('.txt'), 'a') as f:
              for r in x[images == im]:
                  w, h = r[6], r[7]  # image width, height
                  xywh = xyxy2xywh(np.array([[r[1] / w, r[2] / h, r[3] / w, r[4] / h]]))[0]  # instance
                  f.write(f"{cls} {xywh[0]:.5f} {xywh[1]:.5f} {xywh[2]:.5f} {xywh[3]:.5f}\n")  # write label