MULTI-LAYER PERCEPTRON ON MNIST
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
from tensorflow.examples.tutorials.mnist import input_data
%matplotlib inline
print ("PACKAGES LOADED")
PACKAGES LOADED
LOAD MNIST
mnist = input_data.read_data_sets('data/', one_hot=True)
Extracting data/train-images-idx3-ubyte.gz
Extracting data/train-labels-idx1-ubyte.gz
Extracting data/t10k-images-idx3-ubyte.gz
Extracting data/t10k-labels-idx1-ubyte.gz
DEFINE MODEL
n_hidden_1 = 256
n_hidden_2 = 128
n_input = 784
n_classes = 10
x = tf.placeholder("float", [None, n_input])
y = tf.placeholder("float", [None, n_classes])
stddev = 0.1
weights = {
'h1': tf.Variable(tf.random_normal([n_input, n_hidden_1], stddev=stddev)),
'h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2], stddev=stddev)),
'out': tf.Variable(tf.random_normal([n_hidden_2, n_classes], stddev=stddev))
}
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]))
}
print ("NETWORK READY")
NETWORK READY
MLP AS A FUNCTION
def multilayer_perceptron(_X, _weights, _biases):
layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(_X, _weights['h1']), _biases['b1']))
layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, _weights['h2']), _biases['b2']))
return (tf.matmul(layer_2, _weights['out']) + _biases['out'])
DEFINE FUNCTIONS
pred = multilayer_perceptron(x, weights, biases)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
optm = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)
corr = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accr = tf.reduce_mean(tf.cast(corr, "float"))
init = tf.initialize_all_variables()
print ("FUNCTIONS READY")
FUNCTIONS READY
RUN
training_epochs = 20
batch_size = 100
display_step = 4
sess = tf.Session()
sess.run(init)
for epoch in range(training_epochs):
avg_cost = 0.
total_batch = int(mnist.train.num_examples/batch_size)
for i in range(total_batch):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
feeds = {x: batch_xs, y: batch_ys}
sess.run(optm, feed_dict=feeds)
avg_cost += sess.run(cost, feed_dict=feeds)
avg_cost = avg_cost / total_batch
if (epoch+1) % display_step == 0:
print ("Epoch: %03d/%03d cost: %.9f" % (epoch, training_epochs, avg_cost))
feeds = {x: batch_xs, y: batch_ys}
train_acc = sess.run(accr, feed_dict=feeds)
print ("TRAIN ACCURACY: %.3f" % (train_acc))
feeds = {x: mnist.test.images, y: mnist.test.labels}
test_acc = sess.run(accr, feed_dict=feeds)
print ("TEST ACCURACY: %.3f" % (test_acc))
print ("OPTIMIZATION FINISHED")
Epoch: 003/020 cost: 0.124787590
TRAIN ACCURACY: 0.960
TEST ACCURACY: 0.961
Epoch: 007/020 cost: 0.050386614
TRAIN ACCURACY: 0.970
TEST ACCURACY: 0.975
Epoch: 011/020 cost: 0.019682230
TRAIN ACCURACY: 1.000
TEST ACCURACY: 0.979
Epoch: 015/020 cost: 0.007102341
TRAIN ACCURACY: 1.000
TEST ACCURACY: 0.979
Epoch: 019/020 cost: 0.002848990
TRAIN ACCURACY: 1.000
TEST ACCURACY: 0.979
OPTIMIZATION FINISHED