Python 如何修复“AttributeError：模块'tensorflow'没有属性'get_default_graph'”？

How to fix "AttributeError: module 'tensorflow' has no attribute 'get_default_graph'"?

提问by Alice

I am trying to run some code to create an LSTM model but i get an error:

我正在尝试运行一些代码来创建 LSTM 模型，但出现错误：

AttributeError: module 'tensorflow' has no attribute 'get_default_graph'

AttributeError: module 'tensorflow' has no attribute 'get_default_graph'

My code is as follows:

我的代码如下：

from keras.models import Sequential

model = Sequential()
model.add(Dense(32, input_dim=784))
model.add(Activation('relu'))
model.add(LSTM(17))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

I have found someone else with a similar problem and they updated tensorflow and it works; but mine is up to date and still does not work. I am new to using keras and machine learning so I apologise if this is something silly!

我发现其他人有类似的问题，他们更新了 tensorflow 并且它有效；但我的是最新的，仍然无法正常工作。我是使用 keras 和机器学习的新手，所以如果这很愚蠢，我深表歉意！

采纳答案by Alice

Turns out I was using the wrong version (2.0.0a0), so i reset to the latest stable version (1.13.1) and it works.

结果我使用了错误的版本 (2.0.0a0)，所以我重置到最新的稳定版本 (1.13.1) 并且它可以工作。

回答by irezwi

Please try:

请尝试：

from tensorflow.keras.models import Sequential

from tensorflow.keras.models import Sequential

instead of

代替

from keras.models import Sequential

from keras.models import Sequential

回答by Sana

for latest tensorflow 2 replace the above code with below code with some changes

对于最新的 tensorflow 2，将上面的代码替换为下面的代码，并进行一些更改

for details check keras documentation: https://www.tensorflow.org/guide/keras/overview

有关详细信息，请查看 keras 文档：https://www.tensorflow.org/guide/keras/overview

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential, load_model

    model = tf.keras.Sequential()
    model.add(layers.Dense(32, input_dim=784))
    model.add(layers.Activation('relu'))
    model.add(layers.LSTM(17))
    model.add(layers.Dense(1, activation='sigmoid'))
    model.compile(loss='binary_crossentropy', optimizer=tf.keras.optimizers.Adam(0.01), metrics=['accuracy'])

回答by Piyush Chandra

YES, it won't work since you are using the updated version of tensorflow ie tensorflow == 2.0 , the older version of tensorflow might help. I had the same problem but i fixed it using the following code.

是的，它不会工作，因为您使用的是 tensorflow 的更新版本，即 tensorflow == 2.0 ，旧版本的 tensorflow 可能会有所帮助。我遇到了同样的问题，但我使用以下代码修复了它。

try:

尝试：

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.layers import Dropout

instead:

反而：

from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout

回答by palandlom

For tf 2.1.0 I change to tf.compat.v1.get_default_graph()

对于 tf 2.1.0 我改为 tf.compat.v1.get_default_graph()

import tensorflow as tf
# sess = tf.compat.v1.Session(graph=tf.import_graph_def(), config=session_conf)
sess = tf.compat.v1.Session(graph=tf.compat.v1.get_default_graph(), config=session_conf)
tf.compat.v1.keras.backend.set_session(sess)

回答by Jomo

to solve the problem i used the code below

为了解决这个问题，我使用了下面的代码

from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense import numpy

从 tensorflow.keras.models 导入顺序从 tensorflow.keras.layers 导入密集导入 numpy

回答by Hamidreza

Assuming people referring to this thread will be using more and more tensorflow 2:

假设人们参考此线程将使用越来越多的 tensorflow 2：

Tensorflow 2 integrates further keras api, since keras is designed/developed very wisely. The answer is very easy if you are using tensorflow 2, as described also here:

Tensorflow 2 进一步集成了 keras api，因为 keras 的设计/开发非常明智。答案是如果你正在使用tensorflow 2非常容易，也说明这里：

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Activation, LSTM

model = Sequential()
model.add(Dense(32, input_dim=784))
model.add(Activation('relu'))
model.add(LSTM(17))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss=tensorflow.keras.losses.binary_crossentropy, optimizer=tensorflow.keras.optimizers.Adam(), metrics=['accuracy'])

and that's how you change one would use something like MNIST from keras official page with just replacing tensorflow.kerasinstead of kerasand runnig it also on gpu;

这就是你如何改变一个人会使用来自keras官方页面的MNIST之类的东西，只需替换tensorflow.keras而不是 keras在gpu上运行它；

from __future__ import print_function
import tensorflow
from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Flatten
from tensorflow.keras.layers import Conv2D, MaxPooling2D
from tensorflow.keras import backend as K

batch_size = 1024
num_classes = 10
epochs = 12

# input image dimensions
img_rows, img_cols = 28, 28

# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()

if K.image_data_format() == 'channels_first':
    x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
    x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
    input_shape = (1, img_rows, img_cols)
else:
    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
    input_shape = (img_rows, img_cols, 1)

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
y_train = tensorflow.keras.utils.to_categorical(y_train, num_classes)
y_test = tensorflow.keras.utils.to_categorical(y_test, num_classes)

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
             activation='relu',
             input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss=tensorflow.keras.losses.categorical_crossentropy,
          optimizer=tensorflow.keras.optimizers.Adadelta(),
          metrics=['accuracy'])

model.fit(x_train, y_train,
      batch_size=batch_size,
      epochs=epochs,
      verbose=1,
      validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

回答by yash

Use the following:

使用以下内容：

tf.compat.v1.disable_eager_execution()
print(tf.compat.v1.get_default_graph())

It works for tensorflow 2.0

它适用于 tensorflow 2.0

回答by Hannah Zhang

I had the same problem. I tried

我有同样的问题。我试过

   from tensorflow.keras.models import Sequential

and

和

   from keras.models import Sequential

none of them works. So I update tensorflow, keras and python:

他们都没有工作。所以我更新了 tensorflow、keras 和 python：

    $conda update python
    $conda update keras
    $conda update tensorflow

or

或者

    pip install --upgrade tensorflow
    pip install --upgrade keras
    pip install --upgrade python

My tensorflow version is 2.1.0; my keras version is 2.3.1; my python version is 3.6.10. Nothing works until I unintall keras and reinstall keras:

我的 tensorflow 版本是 2.1.0；我的 keras 版本是 2.3.1；我的 python 版本是 3.6.10。在我卸载 keras 并重新安装 keras 之前，什么都不起作用：

    pip uninstall keras
    pip install keras --upgrade

回答by mj.beyrami

Downgrading will fix the problem but if you want to use latest version, you must try this code: from tensorflow import kerasand 'from tensorflow.python.keras import backend as kThat's work for me

降级将解决该问题，但如果您想使用最新版本，则必须尝试以下代码：from tensorflow import keras并且 'from tensorflow.python.keras import backend as k这对我有用