tensorflow with keras example

tf_keras.py

import tensorflow as tf
from keras.metrics import categorical_accuracy as accuracy
sess = tf.Session()

from keras import backend as K
K.set_session(sess)

img = tf.placeholder(tf.float32, shape=(None, 784))

from keras.layers import Dense

# Keras layers can be called on TensorFlow tensors:
x = Dense(128, activation='relu')(img)  # fully-connected layer with 128 units and ReLU activation
x = Dense(128, activation='relu')(x)
preds = Dense(10, activation='softmax')(x)  # output layer with 10 units and a softmax activation

labels = tf.placeholder(tf.float32, shape=(None, 10))

from keras.objectives import categorical_crossentropy
loss = tf.reduce_mean(categorical_crossentropy(labels, preds))

from tensorflow.examples.tutorials.mnist import input_data
mnist_data = input_data.read_data_sets('MNIST_data', one_hot=True)
acc_value = accuracy(labels, preds)

train_step = tf.train.GradientDescentOptimizer(0.5).minimize(loss)
sess.run(tf.global_variables_initializer())
with sess.as_default():
    for i in range(10000):
        batch = mnist_data.train.next_batch(50)
        train_step.run(feed_dict={img: batch[0],
                                  labels: batch[1]})
        print acc_value.eval(feed_dict={img: mnist_data.test.images,
                                    labels: mnist_data.test.labels})