CUB2011

class src.dataset.cub2011.CUB2011(sets, obj_resize)

Data loader for CUB-2011 dataset. Follows train/test split and pair annotations as given by the dataset. Please make sure to configure a correct cfg.CUB2011.ROOT_PATH to make use of this class. Additionally, please note that UCN is evaluated on cleaned up test pairs as provided by WarpNet. Please refer to CUB2011DB_WarpNetTest class for details.

This class is modified from UCN implementation of CUB2011.

get_imgname(data)

get_meta(data)

get_multi(cls=None, num=2, shuffle=True, filter_outlier=False)

Randomly get multiple objects from CUB2011 dataset for multi-matching. :param cls: None for random class, or specify for a certain set :param num: number of objects to be fetched :param shuffle: random shuffle the keypoints :param filter_outlier: filter out outlier keypoints among images :return: (list of data, list of permutation matrices to the universe)

get_pair(cls=None, shuffle=True, tgt_outlier=False, src_outlier=False)

Randomly get a pair of objects from CUB-2011 :param cls: None for random class, or specify for a certain set :param shuffle: random shuffle the keypoints :param tgt_outlier: allow outlier exist in target graph :param src_outlier: allow outlier exist in source graph :return: (pair of data, groundtruth permutation matrix)

len(cls)