AttributeError: 'module' object has no attribute 'normalize_data_format'

从2.2.1后normalize_data_format 就从keras.utils.conv_utils移动到了keras.backend.common，所以keras-contrib 不能通过  keras 2.2.1+ .引入

so

import keras

print(keras.__version__)

可以查看自己的安装Keras版本号

 

所以确定后改为：

from keras.utils.conv_utils import normalize_data_format

```from keras.backend.common import normalize_data_format``

---

https://github.com/keras-team/keras/blob/master/keras/utils/conv_utils.py 

"""Utilities used in convolutional layers.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

from six.moves import range
import numpy as np
from .. import backend as K


def normalize_tuple(value, n, name):
    """Transforms a single int or iterable of ints into an int tuple.
    # Arguments
        value: The value to validate and convert. Could be an int, or any iterable
          of ints.
        n: The size of the tuple to be returned.
        name: The name of the argument being validated, e.g. `strides` or
          `kernel_size`. This is only used to format error messages.
    # Returns
        A tuple of n integers.
    # Raises
        ValueError: If something else than an int/long or iterable thereof was
        passed.
    """
    if isinstance(value, int):
        return (value,) *