是的，这是可能的.

同时导入TensorFlow和Keras，并将您的Keras会话链接到TF一个:

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)

现在，在模型定义中，您可以像这样混合TF和Keras层:

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)

此答案来自 Keras博客由弗朗索瓦·乔尔(Francois Chollet)发表.

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