How to import keras from tf.keras in Tensorflow?

Use the keras module from tensorflow like this:

import tensorflow as tf

Import classes

from tensorflow.python.keras.layers import Input, Dense

or use directly

dense = tf.keras.layers.Dense(...)

EDIT Tensorflow 2

from tensorflow.keras.layers import Input, Dense

and the rest stays the same.

Try from tensorflow.python import keras

with this, you can easily change keras dependent code to tensorflow in one line change.

You can also try from tensorflow.contrib import keras. This works on tensorflow 1.3

Edited: for tensorflow 1.10 and above you can use import tensorflow.keras as keras to get keras in tensorflow.

Its not quite fine to downgrade everytime, you may need to make following changes as shown below:

Tensorflow

import tensorflow as tf

#Keras
from tensorflow.keras.models import Sequential, Model, load_model, save_model
from tensorflow.keras.callbacks import ModelCheckpoint
from tensorflow.keras.layers import Dense, Activation, Dropout, Input, Masking, TimeDistributed, LSTM, Conv1D, Embedding
from tensorflow.keras.layers import GRU, Bidirectional, BatchNormalization, Reshape
from tensorflow.keras.optimizers import Adam

from tensorflow.keras.layers import Reshape, Dropout, Dense,Multiply, Dot, Concatenate,Embedding
from tensorflow.keras import optimizers
from tensorflow.keras.callbacks import ModelCheckpoint

The point is that instead of using

from keras.layers import Reshape, Dropout, Dense,Multiply, Dot, Concatenate,Embedding

you need to add

from tensorflow.keras.layers import Reshape, Dropout, Dense,Multiply, Dot, Concatenate,Embedding

To make it simple I will take the two versions of the code in keras and tf.keras. The example here is a simple Neural Network Model with different layers in it.

In Keras (v2.1.5)

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

def get_model(n_x, n_h1, n_h2):
    model = Sequential()
    model.add(Dense(n_h1, input_dim=n_x, activation='relu'))
    model.add(Dense(n_h2, activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(4, activation='softmax'))
    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
    print(model.summary())
    return model

In tf.keras (v1.9)

import tensorflow as tf

def get_model(n_x, n_h1, n_h2):
    model = tf.keras.Sequential()
    model.add(tf.keras.layers.Dense(n_h1, input_dim=n_x, activation='relu'))
    model.add(tf.keras.layers.Dense(n_h2, activation='relu'))
    model.add(tf.keras.layers.Dropout(0.5))
    model.add(tf.keras.layers.Dense(4, activation='softmax'))
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    print(model.summary())

    return model

or it can be imported the following way instead of the above-mentioned way

from tensorflow.keras.layers import Dense

The official documentation of tf.keras

Note: TensorFlow Version is 1.9