The beginners tutorial mnist-softmax script, from the TensorFlow website. https://www.tensorflow.org/versions/r0.10/tutorials/mnist/beginners/index.html#softmax-regressions

mnist_softmax.py

# https://www.tensorflow.org/versions/r0.10/tutorials/mnist/beginners/index.html#softmax-regressions

# download and read in the data automatically:
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

import tensorflow as tf

# model for handwritten digit [0-9]
# y = softmax(Wx + b)

# x is placeholder, a value that we'll input when we ask TensorFlow to run a computation.
# with shape [None, 784]. (Here None means that a dimension can be of any length.)
x = tf.placeholder(tf.float32, [None, 784])

# W has a shape of [784, 10] because we want to multiply the 784-dimensional 
# image vectors by it to produce 10-dimensional vectors of evidence for the difference classes.
# b has a shape of [10] so we can add it to the output.
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))

# y = softmax(Wx + b)
y = tf.nn.softmax(tf.matmul(x, W) + b)

# training
y_ = tf.placeholder(tf.float32, [None, 10])
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

init = tf.initialize_all_variables()

sess = tf.Session()
sess.run(init)

for i in range(1000):
  batch_xs, batch_ys = mnist.train.next_batch(100)
  sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

# evaluation
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))

accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))