VOC_CLASSES = (  # always index 0
    'aeroplane', 'bicycle', 'bird', 'boat',
    'bottle', 'bus', 'car', 'cat', 'chair',
    'cow', 'diningtable', 'dog', 'horse',
    'motorbike', 'person', 'pottedplant',
    'sheep', 'sofa', 'train', 'tvmonitor')

VOC_IMG_MEAN = (123, 117, 104)  # RGB

COLORS = [[0, 0, 0],
         [128, 0, 0],
         [0, 128, 0],
         [128, 128, 0],
         [0, 0, 128],
         [128, 0, 128],
         [0, 128, 128],
         [128, 128, 128],
         [64, 0, 0],
         [192, 0, 0],
         [64, 128, 0],
         [192, 128, 0],
         [64, 0, 128],
         [192, 0, 128],
         [64, 128, 128],
         [192, 128, 128],
         [0, 64, 0],
         [128, 64, 0],
         [0, 192, 0],
         [128, 192, 0],
         [0, 64, 128]]

# network expects a square input of this dimension
YOLO_IMG_DIM = 448