TensorFlow构建卷积神经网络解mnist2

原理可以看CNN，对图片数据做了卷积池化操作，然后还是用DNN，示意图如下

卷积操作参考卷积
初始化权重与偏移量函数，主要是方便操作

def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)
# help(tf.truncated_normal) 这个函数取给定均值标准差正态分布值<2(标准差-均值)
def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

卷积与池化

# 卷积和池化
def conv2d(x, W):
    # 步长（四个方向）为1，padding:SAME 保持图片大小不变
    return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME')

def max_pool_2x2(x):
    # 第二个参数ksize：池化窗口的大小，取一个四维向量，一般是[1, height, width, 1]，
    # 因为我们不想在batch和channels上做池化，所以这两个维度设为了1
    # 第三个参数strides：和卷积类似，窗口在每一个维度上滑动的步长，
    # 一般也是[1, stride,stride, 1]
    return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1],
                         padding='SAME')

第一层卷积与池化

# 第一层
# 5X5,输入1通道，输出32通道
W_conv1 = weight_variable([5,5,1,32])
b_conv1 = bias_variable([32])
x = tf.placeholder("float", shape=[None, 784])
x_image = tf.reshape(x,[-1,28,28,1])

h_conv1=tf.nn.relu(conv2d(x_image, W_conv1)+b_conv1)
h_pool1=max_pool_2x2(h_conv1)

第二层卷积与池化

# 第二层卷积
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)

全链接层(密集连接层)

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

keep_prob = tf.placeholder('float')
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

输出层

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.global_variables_initializer())
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: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})

最后在测试集上准确率99.19%