Use keras layer in tensorflow code

Question

Lets say I have a simple neural network with an input layer and a single convolution layer programmed in tensorflow:

  # Input Layer
  input_layer = tf.reshape(features["x"], [-1, 28, 28, 1])

  # Convolutional Layer #1
  conv1 = tf.layers.conv2d(
      inputs=input_layer,
      filters=32,
      kernel_size=[5, 5],
      padding="same",
      activation=tf.nn.relu)

I leave out any further parts of the network definitions for the features.

If I wanted to add an LSTM Layer after this convolution layer, I would have to make the convolution layer TimeDistributed (in the language of keras) and then put the output of the TimeDistributed layer into the LSTM.

Tensorflow offers access to the keras layers in tf.keras.layers. Can I use the keras layers directly in the tensorflow code? If so, how? Could I also use the tf.keras.layers.lstm for the implementation of the LSTM Layer?

So in general: Is a mixture of pure tensorflow code and keras code possible and can I use the tf.keras.layers?

I think this question was answered here: stackoverflow.com/questions/42441431/… — ldavid
– ldavid, Commented Nov 8, 2017 at 17:01
Possible duplicate of How to set the input of a Keras layer with a Tensorflow tensor? — ldavid
– ldavid, Commented Nov 8, 2017 at 17:02

collector · Accepted Answer · 2018-03-14 11:15:12Z

17

Yes, this is possible.

Import both TensorFlow and Keras and link your Keras session to the TF one:

import tensorflow as tf
import keras
from keras import backend as K

tf_sess = tf.Session()
K.set_session(tf_sess)

Now, in your model definition, you can mix TF and Keras layers like so:

# Input Layer
input_layer = tf.reshape(features["x"], [-1, 28, 28, 1])

# Convolutional Layer #1
conv1 = tf.layers.conv2d(
    inputs=input_layer,
    filters=32,
    kernel_size=[5, 5],
    padding="same",
    activation=tf.nn.relu)

# Flatten conv output
flat = tf.contrib.layers.flatten(conv1)

# Fully-connected Keras layer
layer2_dense = keras.layers.Dense(128, activation='relu')(flat)

# Fully-connected TF layer (output)
output_preds = tf.layers.dense(layer2_dense, units=10)

This answer is adopted from a Keras blog post by Francois Chollet.

edited Mar 14, 2018 at 11:15

answered Mar 9, 2018 at 11:33

collector

1,0401 gold badge9 silver badges14 bronze badges

Sign up to request clarification or add additional context in comments.

5 Comments

Merlin1896 Over a year ago

So then preds would be a keras layer, right? Is there a way to put this back into a tensorflow layer/operation?

collector Over a year ago

@Merlin1896 You can mix and match any layers you want. I have updated the answer so that the final layer is a standard tensorflow layer

collector Over a year ago

@Merlin1896 if this answered your question you can mark it as answered so that others may find it as well

Merlin1896 Over a year ago

Could you provide a complete minimal example for future reference? The current code won't run :)

collector Over a year ago

@Merlin1896 I changed the example to fit in with your convolutional example. It should run now! In the example I used a Keras dense layer since I'm not sure how exactly you are going to implement the LSTM

Collectives™ on Stack Overflow

Use keras layer in tensorflow code

1 Answer 1

5 Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

5 Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related