In [1]:
# Import TensorFlow
import tensorflow as tf
print(tf.__version__)
In [2]:
# Load MNIST Data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
In [3]:
# Start TensorFlow InteractiveSession
sess = tf.InteractiveSession()
In [3]:
# Placeholders
x = tf.placeholder(tf.float32, shape=[None, 784])
y_ = tf.placeholder(tf.float32, shape=[None, 10])
In [4]:
# Variables
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
In [5]:
# Initialize Variables
sess.run(tf.global_variables_initializer())
In [6]:
# Predicted Class
y = tf.matmul(x,W) + b
In [7]:
# Loss Function
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))
In [9]:
# Train the Model
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
for _ in range(1000):
batch = mnist.train.next_batch(100)
train_step.run(feed_dict={x: batch[0], y_: batch[1]})
In [10]:
# Evaluate the Model
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
In [11]:
# Weight Initialization
def weight_variable(shape):
"""
Initialize weights with a small amount of noise
for symmetry breaking and to prevent 0 gradients
"""
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
"""
Initialize biases with slightly positive values
to avoid ReLU "dead neurons".
"""
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
In [12]:
# Convolution and Pooling
def conv2d(x, W):
"""
Convolution that uses a stride of one and is zero padded
(output is the same size as the input).
"""
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
"""Max pooling over 2x2 blocks."""
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
In [13]:
# First Convolutional Layer
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
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)
In [14]:
# 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)
In [15]:
# 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)
In [17]:
# Readout Layer
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
In [19]:
# Train and Evaluate the Model
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
train_step = tf.train.AdamOptimizer(1e-4).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))
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(1000):
batch = mnist.train.next_batch(50)
if i % 100 == 0:
train_accuracy = accuracy.eval(feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0})
print('step %d, training accuracy %g' % (i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
print('test accuracy %g' % accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))