Convolutional Neural Network with TensorFlow
1. Creation
# Output depth
k_output = 64
# Image Properties
image_width = 10
image_height = 10
color_channels = 3
# Convolution filter
filter_size_width = 5
filter_size_height = 5
# Input/Image
input = tf.placeholder(
tf.float32,
shape=[None, image_height, image_width, color_channels])
# Weight and bias
weight = tf.Variable(tf.truncated_normal(
[filter_size_height, filter_size_width, color_channels, k_output]))
bias = tf.Variable(tf.zeros(k_output))
# Apply Convolution
conv_layer = tf.nn.conv2d(input, weight, strides=[1, 2, 2, 1], padding='SAME')
# Add bias
conv_layer = tf.nn.bias_add(conv_layer, bias)
# Apply activation function
conv_layer = tf.nn.relu(conv_layer)
2. Pooling
2x2 filters with a stride of 2x2 are common in practice.
# Apply Max Pooling
conv_layer = tf.nn.max_pool(
conv_layer,
ksize=[1, 2, 2, 1], #(batch_size, height, width, depth)
strides=[1, 2, 2, 1], #(batch_size, height, width, depth)
padding='SAME')
Padding:
"VALID" = without padding:
inputs: 1 2 3 4 5 6 7 8 9 10 11 (12 13)
|________________| dropped
|_________________|
"SAME" = with zero padding:
pad| |pad
inputs: 0 |1 2 3 4 5 6 7 8 9 10 11 12 13|0 0
|________________|
|_________________|
|________________|
- In this example:
- Input width = 13
- Filter width = 6
- Stride = 5
- Notes:
"VALID"
only ever drops the right-most columns (or bottom-most rows).- `“SAME” tries to pad evenly left and right, but if the amount of columns to be added is odd, it will add the extra column to the right, as is the case in this example (the same logic applies vertically: there may be an extra row of zeros at the bottom).
3. Full examples
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets(".", one_hot=True, reshape=False)
import tensorflow as tf
# Parameters
learning_rate = 0.00001
epochs = 10
batch_size = 128
# Number of samples to calculate validation and accuracy
# Decrease this if you're running out of memory to calculate accuracy
test_valid_size = 256
# Network Parameters
n_classes = 10 # MNIST total classes (0-9 digits)
dropout = 0.75 # Dropout, probability to keep units
# Store layers weight & bias
weights = {
'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])),
'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])),
'wd1': tf.Variable(tf.random_normal([7*7*64, 1024])),
'out': tf.Variable(tf.random_normal([1024, n_classes]))}
biases = {
'bc1': tf.Variable(tf.random_normal([32])),
'bc2': tf.Variable(tf.random_normal([64])),
'bd1': tf.Variable(tf.random_normal([1024])),
'out': tf.Variable(tf.random_normal([n_classes]))}
def conv2d(x, W, b, strides=1):
x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME')
x = tf.nn.bias_add(x, b)
return tf.nn.relu(x)
def maxpool2d(x, k=2):
return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME')
def conv_net(x, weights, biases, dropout):
# Layer 1 - 28*28*1 to 14*14*32
conv1 = conv2d(x, weights['wc1'], biases['bc1'])
conv1 = maxpool2d(conv1, k=2)
# Layer 2 - 14*14*32 to 7*7*64
conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])
conv2 = maxpool2d(conv2, k=2)
# Fully connected layer - 7*7*64 to 1024
fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])
fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
fc1 = tf.nn.relu(fc1)
fc1 = tf.nn.dropout(fc1, dropout)
# Output Layer - class prediction - 1024 to 10
out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])
return out
# tf Graph input
x = tf.placeholder(tf.float32, [None, 28, 28, 1])
y = tf.placeholder(tf.float32, [None, n_classes])
keep_prob = tf.placeholder(tf.float32)
# Model
logits = conv_net(x, weights, biases, keep_prob)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=y))
optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate).minimize(cost)
# Accuracy
correct_pred = tf.equal(tf.argmax(logits, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initializing the variables
init = tf.global_variables_initializer()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
for epoch in range(epochs):
for batch in range(mnist.train.num_examples//batch_size):
batch_x, batch_y = mnist.train.next_batch(batch_size)
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y, keep_prob: dropout})
# Calculate batch loss and accuracy
loss = sess.run(cost, feed_dict={x: batch_x, y: batch_y, keep_prob: 1.})
valid_acc = sess.run(accuracy, feed_dict={
x: mnist.validation.images[:test_valid_size],
y: mnist.validation.labels[:test_valid_size],
keep_prob: 1.})
print('Epoch {:>2}, Batch {:>3} - Loss: {:>10.4f} Validation Accuracy: {:.6f}'.format(
epoch + 1,
batch + 1,
loss,
valid_acc))
# Calculate Test Accuracy
test_acc = sess.run(accuracy, feed_dict={
x: mnist.test.images[:test_valid_size],
y: mnist.test.labels[:test_valid_size],
keep_prob: 1.})
print('Testing Accuracy: {}'.format(test_acc))