Convolution Network


In [1]:
# Adapted notebook from Author: Aymeric Damien
# Project: https://github.com/aymericdamien/TensorFlow-Examples/

In [2]:
# Import MINST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("tmp/data/", one_hot=True)


Extracting tmp/data/train-images-idx3-ubyte.gz
Extracting tmp/data/train-labels-idx1-ubyte.gz
Extracting tmp/data/t10k-images-idx3-ubyte.gz
Extracting tmp/data/t10k-labels-idx1-ubyte.gz

In [3]:
import tensorflow as tf

In [4]:
# Parameters
learning_rate = 0.001
training_iters = 100000
batch_size = 128
display_step = 20

In [5]:
# Network Parameters
n_input = 784 # MNIST data input (img shape: 28*28)
n_classes = 10 # MNIST total classes (0-9 digits)
dropout = 0.75 # Dropout, probability to keep units

In [6]:
# tf Graph input
x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_classes])
keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)

In [7]:
# Create model
def conv2d(img, w, b):
    return tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(img, w, strides=[1, 1, 1, 1], 
                                                  padding='SAME'),b))

def max_pool(img, k):
    return tf.nn.max_pool(img, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME')

def conv_net(_X, _weights, _biases, _dropout):
    # Reshape input picture
    _X = tf.reshape(_X, shape=[-1, 28, 28, 1])

    # Convolution Layer
    conv1 = conv2d(_X, _weights['wc1'], _biases['bc1'])
    # Max Pooling (down-sampling)
    conv1 = max_pool(conv1, k=2)
    # Apply Dropout
    conv1 = tf.nn.dropout(conv1, _dropout)

    # Convolution Layer
    conv2 = conv2d(conv1, _weights['wc2'], _biases['bc2'])
    # Max Pooling (down-sampling)
    conv2 = max_pool(conv2, k=2)
    # Apply Dropout
    conv2 = tf.nn.dropout(conv2, _dropout)

    # Fully connected layer
    # Reshape conv2 output to fit dense layer input
    dense1 = tf.reshape(conv2, [-1, _weights['wd1'].get_shape().as_list()[0]]) 
    # Relu activation
    dense1 = tf.nn.relu(tf.add(tf.matmul(dense1, _weights['wd1']), _biases['bd1']))
    # Apply Dropout
    dense1 = tf.nn.dropout(dense1, _dropout) # Apply Dropout

    # Output, class prediction
    out = tf.add(tf.matmul(dense1, _weights['out']), _biases['out'])
    return out

In [8]:
# Store layers weight & bias
weights = {
    # 5x5 conv, 1 input, 32 outputs
    'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])), 
    # 5x5 conv, 32 inputs, 64 outputs
    'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])), 
    # fully connected, 7*7*64 inputs, 1024 outputs
    'wd1': tf.Variable(tf.random_normal([7*7*64, 1024])), 
    # 1024 inputs, 10 outputs (class prediction)
    '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]))
}

In [9]:
# Construct model
pred = conv_net(x, weights, biases, keep_prob)

In [10]:
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)

In [11]:
# Evaluate model
correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

In [12]:
# Initializing the variables
init = tf.initialize_all_variables()

In [13]:
# Launch the graph
with tf.Session() as sess:
    sess.run(init)
    step = 1
    # Keep training until reach max iterations
    while step * batch_size < training_iters:
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
        # Fit training using batch data
        sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys, keep_prob: dropout})
        if step % display_step == 0:
            # Calculate batch accuracy
            acc = sess.run(accuracy, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
            # Calculate batch loss
            loss = sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
            print "Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
                  "{:.6f}".format(loss) + ", Training Accuracy= " + "{:.5f}".format(acc)
        step += 1
    print "Optimization Finished!"
    # Calculate accuracy for 256 mnist test images
    print "Testing Accuracy:", sess.run(accuracy, feed_dict={x: mnist.test.images[:256], 
                                                             y: mnist.test.labels[:256], 
                                                             keep_prob: 1.})


Iter 2560, Minibatch Loss= 21154.437500, Training Accuracy= 0.30469
Iter 5120, Minibatch Loss= 12081.548828, Training Accuracy= 0.50781
Iter 7680, Minibatch Loss= 11403.013672, Training Accuracy= 0.53125
Iter 10240, Minibatch Loss= 5651.076172, Training Accuracy= 0.70312
Iter 12800, Minibatch Loss= 5953.035645, Training Accuracy= 0.67188
Iter 15360, Minibatch Loss= 2218.375732, Training Accuracy= 0.80469
Iter 17920, Minibatch Loss= 2644.182373, Training Accuracy= 0.78906
Iter 20480, Minibatch Loss= 1479.909546, Training Accuracy= 0.87500
Iter 23040, Minibatch Loss= 1315.046265, Training Accuracy= 0.91406
Iter 25600, Minibatch Loss= 3178.376709, Training Accuracy= 0.77344
Iter 28160, Minibatch Loss= 2294.122559, Training Accuracy= 0.81250
Iter 30720, Minibatch Loss= 1196.053589, Training Accuracy= 0.84375
Iter 33280, Minibatch Loss= 1676.132812, Training Accuracy= 0.85156
Iter 35840, Minibatch Loss= 428.335327, Training Accuracy= 0.92969
Iter 38400, Minibatch Loss= 340.574097, Training Accuracy= 0.95312
Iter 40960, Minibatch Loss= 1397.641113, Training Accuracy= 0.89844
Iter 43520, Minibatch Loss= 558.186829, Training Accuracy= 0.92188
Iter 46080, Minibatch Loss= 606.679749, Training Accuracy= 0.95312
Iter 48640, Minibatch Loss= 1555.515625, Training Accuracy= 0.88281
Iter 51200, Minibatch Loss= 384.410248, Training Accuracy= 0.92188
Iter 53760, Minibatch Loss= 362.374695, Training Accuracy= 0.95312
Iter 56320, Minibatch Loss= 807.723511, Training Accuracy= 0.92969
Iter 58880, Minibatch Loss= 544.502686, Training Accuracy= 0.94531
Iter 61440, Minibatch Loss= 863.515930, Training Accuracy= 0.92188
Iter 64000, Minibatch Loss= 836.524353, Training Accuracy= 0.89844
Iter 66560, Minibatch Loss= 656.470886, Training Accuracy= 0.93750
Iter 69120, Minibatch Loss= 856.812866, Training Accuracy= 0.89844
Iter 71680, Minibatch Loss= 580.534241, Training Accuracy= 0.94531
Iter 74240, Minibatch Loss= 708.007568, Training Accuracy= 0.91406
Iter 76800, Minibatch Loss= 971.588013, Training Accuracy= 0.91406
Iter 79360, Minibatch Loss= 383.844879, Training Accuracy= 0.92969
Iter 81920, Minibatch Loss= 909.780396, Training Accuracy= 0.91406
Iter 84480, Minibatch Loss= 600.898804, Training Accuracy= 0.95312
Iter 87040, Minibatch Loss= 267.563171, Training Accuracy= 0.96094
Iter 89600, Minibatch Loss= 772.752686, Training Accuracy= 0.89844
Iter 92160, Minibatch Loss= 613.072388, Training Accuracy= 0.91406
Iter 94720, Minibatch Loss= 433.241302, Training Accuracy= 0.96094
Iter 97280, Minibatch Loss= 684.323486, Training Accuracy= 0.92969
Iter 99840, Minibatch Loss= 563.071777, Training Accuracy= 0.92188
Optimization Finished!
Testing Accuracy: 0.964844

In [ ]: