tensorflow tutorial - MNIST data

mnist_conv.py

# coding: utf-8
import input_data
mnist = input_data.read_data_sets('MNIST_data/', one_hot=True)

import tensorflow as tf

# training parameters
learning_rate = 1e-4
training_iteration = 4
batch_size = 50

# helper methods to initialize weights and biases
def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)

def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

# TODO: strides? wat is it?
def conv2d(x, W):
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')

x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])

# first convolutional layer
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])

# reshape x to a 4d tensor
x_image = tf.reshape(x, [-1, 28, 28, 1])

h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

# second convolutional layer
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

# densely connected layer
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

# dropout
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

# readout layer
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

# train the model
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
train_step = tf.train.AdamOptimizer(learning_rate).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())

print('Total number of training/test examples: %d/%d' % (mnist.train.num_examples, mnist.test.num_examples))

total_batch = int(mnist.train.num_examples / batch_size)
for i in range(training_iteration):
    print('epoch: %d, test accuracy: %05f' % (i, accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0})))

    for j in range(total_batch):
        batch = mnist.train.next_batch(batch_size)
        sess.run(train_step, feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

        if j % 100 == 0:
            train_accuracy = accuracy.eval(feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0})
            print('step: %d/%d/%d, training accuracy: %05f' % (j, total_batch, i, train_accuracy))

print('test accuracy: %05f' % accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

mnist_softmax.py

# coding: utf-8
import input_data
mnist = input_data.read_data_sets('MNIST_data/', one_hot=True)

import tensorflow as tf

learning_rate = 0.2
training_iteration = 30
batch_size = 100
display_step = 2

# create the model
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.matmul(x, W) + b

y_ = tf.placeholder(tf.float32, [None, 10])

cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(cross_entropy)

sess = tf.InteractiveSession()
tf.global_variables_initializer().run()

# train
total_batch = int(mnist.train.num_examples / batch_size)

for i in range(training_iteration):
    for _ in range(total_batch):
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
        sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

    predictions = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
    accuracy = tf.reduce_mean(tf.cast(predictions, tf.float32))
    print('Iteration: %04d, accuracy: %.04f' %(i, sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels})))