In [1]:

    

import tensorflow as tf
sess = tf.Session()

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


    

    




Using TensorFlow backend.

In [2]:

    

# this placeholder will contain our input digits, as flat vectors
img = tf.placeholder(tf.float32, shape=(None, 784))


    

In [3]:

    

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


    

In [4]:

    

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

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


    

In [5]:

    

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

train_step = tf.train.GradientDescentOptimizer(0.5).minimize(loss)

sess.run(tf.global_variables_initializer())  # - required for Tensorflow variable initialization

with sess.as_default():
    for i in range(100):
        batch = mnist_data.train.next_batch(50)
        train_step.run(feed_dict={img: batch[0],
                                  labels: batch[1]})


    

    




Successfully downloaded train-images-idx3-ubyte.gz 9912422 bytes.
Extracting MNIST_data/train-images-idx3-ubyte.gz
Successfully downloaded train-labels-idx1-ubyte.gz 28881 bytes.
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Successfully downloaded t10k-images-idx3-ubyte.gz 1648877 bytes.
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Successfully downloaded t10k-labels-idx1-ubyte.gz 4542 bytes.
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz

In [ ]: