ImportError: cannot import name 'normalize_data_format'

Question

我读过一篇文章 Here and its pretty nice enough to understand. Given its implementation on GitHub. When I am trying to train at my own using given code it gives me an Import Error in this file at line 117 ，如下所示。我正在使用 google Colab 环境。对错误进行一些搜索后，我发现以下行与 keras 版本==2.2.2 兼容。我也安装了它但没有解决错误。请帮助我克服它。 colab 中默认安装的 keras 版本是 2.2.4

---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
<ipython-input-47-f8ce7e15cf87> in <module>()
      9 from keras.layers.merge import Add
     10 from keras.utils import conv_utils
---> 11 from keras.utils.conv_utils import normalize_data_format
     12 
     13 from keras.layers.core import Dropout

ImportError: cannot import name 'normalize_data_format'

---------------------------------------------------------------------------

Answer 1

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

master 分支的 conv_utils 没有 normalize_data_format。其他一些分支机构确实有它，例如 tf-keras 分支机构。这是一个简单的函数，这里是它的实现：

import keras.backend as K
def normalize_data_format(value):
    if value is None:
        value = K.image_data_format()
    data_format = value.lower()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('The `data_format` argument must be one of '
                         '"channels_first", "channels_last". Received: ' +
                         str(value))
    return data_format

ImportError: cannot import name 'normalize_data_format'

ImportError: cannot import name 'normalize_data_format'

python-3.x

deep-learning

conv-neural-network

keras

keras-layer