model.py 文件源码

def load_from_hdf5(self, path):
        """load model in compressed sparse row format from hdf5 file

        hdf5 file should contain row_ptr, col_ind and data array

        Args:
            path: path to the embeddings folder
        """
        self.load_metadata(path)
        f = tables.open_file(os.path.join(path, 'cooccurrence_csr.h5p'), 'r')
        row_ptr = np.nan_to_num(f.root.row_ptr.read())
        col_ind = np.nan_to_num(f.root.col_ind.read())
        data = np.nan_to_num(f.root.data.read())
        dim = row_ptr.shape[0] - 1
        self.matrix = scipy.sparse.csr_matrix(
            (data, col_ind, row_ptr), shape=(dim, dim), dtype=np.float32)
        f.close()
        self.vocabulary = Vocabulary_cooccurrence()
        self.vocabulary.load(path)
        self.name += os.path.basename(os.path.normpath(path))