Tensorflow 實現簡單CNN 數字識別

卷積的好處是，不管圖片尺寸如何，我們需要訓練的權值數量只和卷積核大小、卷積核數量有關。
每個卷積層包含三個部分：卷積、池化和非線性激活函數

__author__ = 'ding'
'''
Tensorflow 實現簡單CNN
'''
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets('./MNIST_data', one_hot=True)
sess = tf.InteractiveSession()


# 初始化CNN的權重
def weight_variable(shape):
    initial = tf.truncated_normal(shape=shape, stddev=0.1)
    return tf.Variable(initial)


# 初始化CNN的偏置
def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)


# 卷積層定義
def conv2d(x, W):
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')


# 池化層定義
def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')


# 定義輸入的placeholder
# x_image 使用reshape將1*784的形式轉換成原始形式28*28  -1代表樣本數量不固定，1代表顏色通道數量
x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
x_image = tf.reshape(x, [-1, 28, 28, 1])

# 定義第一層卷積層
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 = max_pool_2x2(h_conv1)

# 第二層卷積層
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 = max_pool_2x2(h_conv2)

#
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)

# dropout層 用來減少過擬合
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

# 將dropout層輸出連接一個softmax層 得到概率輸出
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)

# 定義損失函數
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

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

init = tf.global_variables_initializer()
sess.run(init)

for i in range(20000):
    batch = mnist.train.next_batch(50)
    if i % 100 == 0:
        train_accuracy = sess.run(accuracy, feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.1})
        print('step %d, training accuracy %g' % (i, train_accuracy))

    sess.run(train_step, feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
print('test accuracy %g' % sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

利用CNN網絡來進行圖像識別 準確率達到99.2% 比之前的簡單的神經網絡識別率要高出不少。