Tensorflow--MNIST手寫數據集卷積層分類

接上一篇文章，在圖像領域用的最多的就是CNN，卷積神經網絡。用CNN來做分類當然也是必不可少的。

# 用tensorflow 導入數據
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
# 權值初始化
def weight_variable(shape):
    # 用正態分佈來初始化權值
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)

def bias_variable(shape):
    # 本例中用relu激活函數，所以用一個很小的正偏置較好
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

# 定義卷積層
def conv2d(x, W):
    # 默認 strides[0]=strides[3]=1, strides[1]爲x方向步長，strides[2]爲y方向步長
    return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME')

# pooling 層
def max_pool_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])
y_ = tf.placeholder(tf.float32, [None, 10])

# 把X轉爲卷積所需要的形式
X = tf.reshape(X_, [-1, 28, 28, 1])
# 第一層卷積：5×5×1卷積核32個 [5，5，1，32]
W_conv1 = weight_variable([5,5,1,32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(X, W_conv1) + b_conv1)

# 第一個pooling 層
h_pool1 = max_pool_2x2(h_conv1)

# 第二層卷積：5×5×32卷積核64個 [5，5，32，64]
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)

# 第二個pooling 層,輸出[None, 7, 7, 64] ? 
h_pool2 = max_pool_2x2(h_conv2)

# flatten
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])

# fc1
W_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

# dropout: 輸出的維度和h_fc1一樣，只是隨機部分值被值爲零
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

# 輸出層
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)

cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
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, "float"))
sess.run(tf.initialize_all_variables())
for i in range(10000):
    batch = mnist.train.next_batch(50)
    if i%1000 == 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)
    train_step.run(feed_dict={X_: batch[0], y_: batch[1], keep_prob: 0.5})

print "test accuracy %g"%accuracy.eval(feed_dict={
    X_: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0})