TensorFlow笔记之简单cnn

mnist上达到了99.22%的正确率

# -*- coding:utf-8 -*-
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf

# data
dir = '/home/kaka/Documents/input_data'
mnist = input_data.read_data_sets(dir, one_hot=True)

sess = tf.InteractiveSession()

def weight_variable(shape):
    initial =tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)

def bias_variable(shape):
    initial=tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

def conv2d(x,w):
    return tf.nn.conv2d(x, w, strides=[1, 1, 1, 1], padding='SAME')

def maxpool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')

x = tf.placeholder(tf.float32, [None, 784])
x_image = tf.reshape(x, [-1, 28, 28, 1])
y_ = tf.placeholder(tf.float32, [None, 10])

# conv1
w_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, w_conv1) + b_conv1)
h_pool1 = maxpool_2x2(h_conv1)

# conv2
w_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, w_conv2) + b_conv2)
h_pool2 = maxpool_2x2(h_conv2)

# fc1
w_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, w_fc1) + b_fc1)

# fc1 dropout
keep_prob = tf.placeholder(tf.float32)   #dropout proportion
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

w_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, w_fc2) + b_fc2)

# loss
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

# accuray
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

tf.global_variables_initializer().run()
for i in range(20000):
    batch = mnist.train.next_batch(100)
    if i % 100 == 0:
        train_accuracy = accuracy.eval(feed_dict={
            x: batch[0], y_: batch[1], keep_prob: 1.0})
        print('step %d, training accuracy %g' % (i, train_accuracy))
    sess.run(train_step, feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.75})

print(sess.run(accuracy, feed_dict={
    x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))