h5py, access data in Datasets in SVHN

I'll answer my question here, after read the docs of h5py, here is my code

def get_box_data(index, hdf5_data):
    """
    get `left, top, width, height` of each picture
    :param index:
    :param hdf5_data:
    :return:
    """
    meta_data = dict()
    meta_data['height'] = []
    meta_data['label'] = []
    meta_data['left'] = []
    meta_data['top'] = []
    meta_data['width'] = []

    def print_attrs(name, obj):
        vals = []
        if obj.shape[0] == 1:
            vals.append(obj[0][0])
        else:
            for k in range(obj.shape[0]):
                vals.append(int(hdf5_data[obj[k][0]][0][0]))
        meta_data[name] = vals

    box = hdf5_data['/digitStruct/bbox'][index]
    hdf5_data[box[0]].visititems(print_attrs)
    return meta_data

def get_name(index, hdf5_data):
    name = hdf5_data['/digitStruct/name']
    return ''.join([chr(v[0]) for v in hdf5_data[name[index][0]].value])

Here the hdf5_data is train_data = h5py.File('./train/digitStruct.mat'), it works fine!

Update

Here is some sample code to use the above two functions

mat_data = h5py.File(os.path.join(folder, 'digitStruct.mat'))
size = mat_data['/digitStruct/name'].size

for _i in tqdm.tqdm(range(size)):
    pic = get_name(_i, mat_data)
    box = get_box_data(_i, mat_data)

The above function shows how to get the name and the bbox data of each entry of the data!