來自<Tensorflow實戰>一書

# 兩個卷積　一個全連線層
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
sess = tf.InteractiveSession()

# 有許多權重偏置要建立，先定義倆留著用
def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev
 
= 0.1)  # 標準差0.1
return tf.Variable(initial)
def bias_variable(shape):
    initial = tf.constant(0.1,shape=shape)  # 偏置增加小正值防止死亡節點
return tf.Variable(initial)
# 定義卷積層和池化層
def conv2d(x, W):
    return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME')  # 卷積的輸出輸入保持同樣的尺寸  # strides[圖片，長，寬，channel]
def 
 
max_pool_2x2(x):
    return tf.nn.max_pool(x,ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
# 定義輸入空間
x = tf.placeholder(tf.float32,[None, 784])
y_ = tf.placeholder(tf.float32,[None,10])
x_image = tf.reshape(x, [-1,28,28,1])

# 第一個卷積層+池化
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)

# 第二個卷積層+池化
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)

# 連一個全連線層
W_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])  # 把第二個卷積層的輸出reshape成1Ｄ的
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

# Dropout層
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

# Softmax層
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)

# Adam優化器＋cross entropy＋小學習速率
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)

# 評測準確率
correct_prediction = tf.equal(tf.argmax(y_conv,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

# 訓練
tf.global_variables_initializer().run()
for i in range(20000):
    batch = mnist.train.next_batch(50)
    if i%100 == 0:
        train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_: batch[1], keep_prob: 0.5})
        print("step %d, training accuracy %g"%(i,train_accuracy))
    train_step.run(feed_dict={x:batch[0], y_: batch[1], keep_prob: 1.0})

# 全部訓練完成　測試
print("test accuracy ％g"%accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))