- # 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
- # /datasets/SKU-110K
- # /yolov5
-
-
- # 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/SKU-110K # dataset root dir
- train: train.txt # train images (relative to 'path') 8219 images
- val: val.txt # val images (relative to 'path') 588 images
- test: test.txt # test images (optional) 2936 images
-
- # Classes
- nc: 1 # number of classes
- names: [ 'object' ] # class names
-
-
- # Download script/URL (optional) ---------------------------------------------------------------------------------------
- download: |
- import shutil
- from tqdm import tqdm
- from utils.general import np, pd, Path, download, xyxy2xywh
-
- # Download
- dir = Path(yaml['path']) # dataset root dir
- parent = Path(dir.parent) # download dir
- urls = ['http://trax-geometry.s3.amazonaws.com/cvpr_challenge/SKU110K_fixed.tar.gz']
- download(urls, dir=parent, delete=False)
-
- # Rename directories
- if dir.exists():
- shutil.rmtree(dir)
- (parent / '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
|
