适用于 Keras 2.3 的 Tensorflow 包

Shi*_*ata 3 python-3.x keras tensorflow

我尝试在我的计算机上使用 Keras,但不断收到错误消息“AttributeError:模块‘tensorflow.python.keras.backend’没有属性‘get_graph’”。

堆栈跟踪是:

---------------------------------------------------------------------------
 AttributeError                            Traceback (most recent call last)
<ipython-input-1-dd13cebc6f04> in <module>
----> 1 import acgan

~/Documents/GitHub/Keras-GAN/acgan/acgan.py in <module>
  1 from __future__ import print_function, division
  2 
 ----> 3 from keras.datasets import mnist
  4 from keras.layers import Input, Dense, Reshape, Flatten, Dropout, multiply
  5 from keras.layers import BatchNormalization, Activation, Embedding, ZeroPadding2D

/anaconda3/lib/python3.6/site-packages/keras/__init__.py in <module>
  1 from __future__ import absolute_import
  2 
 ----> 3 from . import utils
  4 from . import activations
  5 from . import applications

/anaconda3/lib/python3.6/site-packages/keras/utils/__init__.py in <module>
  4 from . import data_utils
  5 from . import io_utils
 ----> 6 from . import conv_utils
  7 from . import losses_utils
  8 from . import metrics_utils

 /anaconda3/lib/python3.6/site-packages/keras/utils/conv_utils.py in <module>
  7 from six.moves import range
  8 import numpy as np
  ----> 9 from .. import backend as K
 10 
 11 

 /anaconda3/lib/python3.6/site-packages/keras/backend/__init__.py in <module>
 ----> 1 from .load_backend import epsilon
  2 from .load_backend import set_epsilon
  3 from .load_backend import floatx
  4 from .load_backend import set_floatx
  5 from .load_backend import cast_to_floatx

 /anaconda3/lib/python3.6/site-packages/keras/backend/load_backend.py in <module>
 88 elif _BACKEND == 'tensorflow':
 89     sys.stderr.write('Using TensorFlow backend.\n')
 ---> 90     from .tensorflow_backend import *
 91 else:
 92     # Try and load external backend.

 /anaconda3/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py in <module>
 52 
 53 # Private TF Keras utils
 ---> 54 get_graph = tf_keras_backend.get_graph
 55 # learning_phase_scope = tf_keras_backend.learning_phase_scope  # 
TODO
 56 name_scope = tf.name_scope

AttributeError: module 'tensorflow.python.keras.backend' has no attribute 'get_graph'
Run Code Online (Sandbox Code Playgroud)

我用谷歌搜索了这个问题并发现了这个

https://forums.xilinx.com/t5/Deephi-DNNDK/Module-tensorflow-python-keras-backend-has-no-attribute-get/td-p/1022555

这告诉我它与张量流版本相关,但不告诉我要使用哪个版本。我在 MacOS 上使用 Python3。

感谢您的帮助。

Man*_*han 5

我无法重现您在 Keras 2.3.0 和 tensorflow 2.0.0rc1 中观察到的错误。虽然我能够开始 acgan 的训练,但在一次迭代后我得到了一个不同的错误:Resource localhost/_AnonymousVar84/N10tensorflow3VarE does not exist

我可以使用以下版本成功运行该示例:

  1. 喀拉斯 2.2.4/张量流 1.14.0
  2. tensorflow 2.0.0rc1 并替换kerastensorflow.keras导入中的。