TensorFlow using MNIST. Using standard TF APIs, in 30 lines of code.

mnist2.py

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

session = tf.Session()
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

input = tf.placeholder(tf.float32, shape=(None, 784))
x = tf.layers.dense(input, 128, activation=tf.nn.relu) # layer 1
x = tf.layers.dense(x, 128, activation=tf.nn.relu) # layer 2
x = tf.layers.dense(x, 10, activation=None) # layer 3
y = tf.nn.softmax(x)

label = tf.placeholder(tf.float32, (None, 10))
loss = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits_v2(labels=label, logits=x) ) 

optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.1)
train_op = optimizer.minimize(loss)

session.run(tf.global_variables_initializer())

for i in range(0, 10000):
    batch_xs, batch_ys = mnist.train.next_batch(64)
    _, current_loss = session.run([train_op, loss], feed_dict={  input: batch_xs, label: batch_ys })
    print("[%d.] Current Loss: %f" % (i, current_loss))

batch_xs, batch_ys = mnist.train.next_batch(1)
_y = session.run(y, feed_dict={ input: batch_xs })
print("Model prediction: %s \nActual label: %s" % (_y[0], batch_ys[0]))

session.close()