CNN MNIST Example Tensorflow

CNN MNIST Example Code

import tensorflow as tf
import random
from tensorflow.examples.tutorials.mnist import input_data

tf.set_random_seed(777)
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
r = random.randint(0, mnist.test.num_examples - 1)

class Model:
    def __init__(self, sess, name):
        self.sess = sess
        self.name = name
        self.Layers()

    # build model
    def Layers(self):
        with tf.variable_scope(self.name):
            # set placeholder variables
            self.X = tf.placeholder(tf.float32, [None, 784])
            X_img = tf.reshape(self.X, [-1, 28, 28, 1])
            self.Y = tf.placeholder(tf.float32, [None, 10])

            # set Layers
            conv1 = tf.layers.conv2d(inputs=X_img, filters=6, kernel_size=[3, 3],
                                     padding="SAME", activation=tf.nn.relu)
            pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], padding="SAME", strides=2)
            dropout1 = tf.layers.dropout(inputs=pool1, rate=0.3)

            conv2 = tf.layers.conv2d(inputs=dropout1, filters=12, kernel_size=[3, 3],
                                     padding="SAME", activation=tf.nn.relu)
            pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], padding="SAME", strides=2)
            dropout2 = tf.layers.dropout(inputs=pool2, rate=0.3)

            conv3 = tf.layers.conv2d(inputs=dropout2, filters=24, kernel_size=[3, 3],
                                     padding="same", activation=tf.nn.relu)
            pool3 = tf.layers.max_pooling2d(inputs=conv3, pool_size=[2, 2], padding="same", strides=2)
            dropout3 = tf.layers.dropout(inputs=pool3, rate=0.3)

            flat = tf.reshape(dropout3, [-1, 24 * 4 * 4])
            dense4 = tf.layers.dense(inputs=flat, units=100, activation=tf.nn.relu)
            dropout4 = tf.layers.dropout(inputs=dense4, rate=0.5)

            self.logits = tf.layers.dense(inputs=dropout4, units=10)

        # loss & optimizer
        self.cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=self.logits, labels=self.Y))
        self.optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(self.cost)

        correct_prediction = tf.equal(tf.argmax(self.logits, 1), tf.argmax(self.Y, 1))
        self.accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    def get_predict(self, x_test, y_test):
        print("Test Label: ", sess.run(tf.argmax(y_test, 1)))
        print("Prediction Label: ", sess.run(tf.argmax(self.logits, 1), feed_dict={self.X: x_test}))
        return

    def get_accuracy(self, x_test, y_test):
        print('Test Data Set Accuracy:',self.sess.run(self.accuracy, feed_dict={self.X: x_test, self.Y: y_test}))
        return

    def train(self, x_data, y_data):
        return self.sess.run([self.cost, self.optimizer], feed_dict={self.X: x_data, self.Y: y_data})

# Main

# set learning_rate , epochs, batch_size
learning_rate = 0.001
training_epochs = 5
batch_size = 100

sess = tf.Session()
model = Model(sess, "model")
sess.run(tf.global_variables_initializer())

print("Learning start.")
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)
        c, _ = model.train(batch_xs, batch_ys)
        avg_cost += c / total_batch
    print('Epoch:', '%04d' % (epoch + 1), 'cost =', '{:.9f}'.format(avg_cost))
print('Learning Finish!')

# Evaluation
model.get_accuracy(mnist.test.images, mnist.test.labels)
model.get_predict(mnist.test.images[r:r + 1],mnist.test.labels[r:r + 1])
sess.close()