tensorflow - 没有名为 'tensorflow.keras.layers.experimental.preprocessing' 的模块

Question

代码下方

import numpy as np
np.random.seed(0)
from sklearn import datasets
import matplotlib.pyplot as plt
%matplotlib inline
%config InlineBackend.figure_format ='retina'

from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import SGD

在错误消息 下方

---------------------------------------------------------------------------
ModuleNotFoundError                       Traceback (most recent call last)
~\Anaconda3\lib\site-packages\keras\__init__.py in <module>
      2 try:
----> 3     from tensorflow.keras.layers.experimental.preprocessing import RandomRotation
      4 except ImportError:

ModuleNotFoundError: No module named 'tensorflow.keras.layers.experimental.preprocessing'

During handling of the above exception, another exception occurred:

ImportError                               Traceback (most recent call last)
<ipython-input-5-943507dd87a6> in <module>
      6 get_ipython().run_line_magic('config', "InlineBackend.figure_format ='retina'")
      7 
----> 8 from keras.models import Sequential
      9 from keras.layers import Dense
     10 from keras.optimizers import SGD

~\Anaconda3\lib\site-packages\keras\__init__.py in <module>
      4 except ImportError:
      5     raise ImportError(
----> 6         'Keras requires TensorFlow 2.2 or higher. '
      7         'Install TensorFlow via `pip install tensorflow`')
      8 

ImportError: Keras requires TensorFlow 2.2 or higher. Install TensorFlow via `pip install tensorflow

注意:` 我认为，主要问题是 Tensorflow 版本。我使用了 somes 命令，如下所示，

conda create -n tf tensorflow
conda activate tf

我还使用了以下命令

conda create -n tf-gpu tensorflow-gpu
conda activate tf-gpu

但它不起作用，请帮助解决错误。

Answer 1

您需要更新 TensorFlow 的版本。对我来说，2.2.0 解决了这个问题。我还检查了更高版本并且工作正常。

pip install tensorflow==2.2.0

或者

pip install tensorflow-gpu==2.2.0