Multilayer Perceptron


In [1]:
# Import MINST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("tmp/data/", one_hot=True)

import tensorflow as tf


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 [2]:
# Parameters
learning_rate = 0.01
training_epochs = 15
batch_size = 100
display_step = 1

# Network Parameters
n_hidden_1 = 256 # 1st layer number of features
n_hidden_2 = 256 # 2nd layer number of features
n_input = 784 # MNIST data input (img shape: 28*28)
n_classes = 10 # MNIST total classes (0-9 digits)

# tf Graph input
x = tf.placeholder("float", [None, n_input])
y = tf.placeholder("float", [None, n_classes])

In [3]:
# Create model
def multilayer_perceptron(x, weights, biases):
    # Hidden layer with RELU activation
    layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1'])
    layer_1 = tf.nn.relu(layer_1)
    # Hidden layer with RELU activation
    layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2'])
    layer_2 = tf.nn.relu(layer_2)
    # Output layer with linear activation
    out_layer = tf.matmul(layer_2, weights['out']) + biases['out']
    return out_layer

In [4]:
# Store layers weight & bias
weights = {
    'h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),
    'h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),
    'out': tf.Variable(tf.random_normal([n_hidden_2, n_classes]))
}
biases = {
    'b1': tf.Variable(tf.random_normal([n_hidden_1])),
    'b2': tf.Variable(tf.random_normal([n_hidden_2])),
    'out': tf.Variable(tf.random_normal([n_classes]))
}

# Construct model
pred = multilayer_perceptron(x, weights, biases)

# 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)

# Initializing the variables
init = tf.initialize_all_variables()

In [5]:
# Launch the graph
with tf.Session() as sess:
    sess.run(init)

    # Training cycle
    for epoch in range(training_epochs):
        avg_cost = 0.
        total_batch = int(mnist.train.num_examples/batch_size)
        # Loop over all batches
        for i in range(total_batch):
            batch_x, batch_y = mnist.train.next_batch(batch_size)
            # Run optimization op (backprop) and cost op (to get loss value)
            _, c = sess.run([optimizer, cost], feed_dict={x: batch_x,
                                                          y: batch_y})
            # Compute average loss
            avg_cost += c / total_batch
        # Display logs per epoch step
        if epoch % display_step == 0:
            print "Epoch:", '%04d' % (epoch+1), "cost=", \
                "{:.9f}".format(avg_cost)
    print "Optimization Finished!"

    # Test model
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
    # Calculate accuracy
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
    print "Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels})


Epoch: 0001 cost= 49.995715293
Epoch: 0002 cost= 8.220254425
Epoch: 0003 cost= 4.781198184
Epoch: 0004 cost= 3.137418295
Epoch: 0005 cost= 2.593291543
Epoch: 0006 cost= 2.198339433
Epoch: 0007 cost= 2.000956071
Epoch: 0008 cost= 1.699920031
Epoch: 0009 cost= 1.547363868
Epoch: 0010 cost= 1.438938281
Epoch: 0011 cost= 1.157734862
Epoch: 0012 cost= 1.165930717
Epoch: 0013 cost= 1.009958370
Epoch: 0014 cost= 1.039777737
Epoch: 0015 cost= 0.853928272
Optimization Finished!
Accuracy: 0.9595

Exercice 1

Modify the architecture of the network. You can add extra hidden layers and/or the number of neurons per layer. How do you obtain the best results?


In [ ]:


In [ ]:


In [ ]: