TensorFlow-3 CNN数字识别

1 理论

卷积神经网络（CNN）的理论内容请参考：卷积神经网络概念与原理

         2 CNN网络结构

利用CNN进行MNist数字识别，两层卷积层，两层池化层
1层卷积层:Size（5,5）,Stride(1), 32feature Map 激活函数为RELU
1层池化层：Size（2,2），最大池化
2层卷积层：Size(5,5),Stride(1), 64feature Map 激活函数为RELU
2层池化层：Size(2,2),最大池化
1全连接层：1024特征

    2全连接层：10个输出（softmax分类器）

3 代码实现

import tensorflow.examples.tutorials.mnist.input_data as inputData
import tensorflow as tf

mnist=inputData.read_data_sets('MNIST_data',one_hot=True)

def compute_accuracy(t_xs,t_ys):
    global y
    prediction=tf.nn.softmax(y)
    #sess.run(prediction,feed_dict={xs:t_xs,keep_pro:1})
    correct_prdiction=tf.equal(tf.argmax(prediction,1),tf.argmax(t_ys,1))
    accuracy=tf.reduce_mean(tf.cast(correct_prdiction,tf.float32))
    result=sess.run(accuracy,feed_dict={xs:t_xs,ys:t_ys,keep_pro:1})
    return result

#定义weight变量
def weight_Variables(shape):
    initial=tf.truncated_normal(shape,stddev=0.1)
    return tf.Variable(initial)

#定义bias变量
def bias_Variable(shape):
    initial=tf.constant(0.1,shape=shape)
    return tf.Variable(initial)

#卷积函数
def cov2d(x,W):
     # stride [1, x_movement, y_movement, 1]
    # 必有 strides[0] = strides[3] = 1
    return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')

#定义池化层
def max_pool_2X2(x):
    #Size（2,2），最大池化
    return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')


#1 define the place holder for the train data
xs=tf.placeholder(tf.float32,[None,784])#28*28
ys=tf.placeholder(tf.float32,[None,10])#labels
keep_pro=tf.placeholder(tf.float32)
x_image=tf.reshape(xs,[-1,28,28,1])#1means黑白
print(x_image.shape) #[nsamples,28,28]

#2 ===Cov1 layer====
W_cov1=weight_Variables([5,5,1,32]) #Size（5,5）,Stride(1), 32feature Map
b_cov1=bias_Variable([32])
#利用Relu激励函数构建第一个卷积层
h_conv1=tf.nn.relu(cov2d(x_image,W_cov1)+b_cov1)
#第1层池化，池化后Size[14,14]
h_pool1=max_pool_2X2(h_conv1)

#3 ===Cov2 layer====
W_cov2=weight_Variables([5,5,32,64]) #Size（5,5）,Stride(1), 64feature Map
b_cov2=bias_Variable([64])
#利用Relu激励函数构建第2个卷积层
h_conv1=tf.nn.relu(cov2d(h_pool1, W_cov2)+b_cov2)
#第2层池化，池化后Size[7,7]
h_pool2=max_pool_2X2(h_conv1)

#4 ===全连接层1（fully connected layer)====
W_fc1=weight_Variables([7*7*64,1024]) #1024特征
b_fc1=bias_Variable([1024])
#将h_pool2变平，即[nsamples,7,7,64]->[nsamples,7*7*64]
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,增强模型的泛化能力
h_fc1_drop=tf.nn.dropout(h_fc1,keep_pro)

#5 ===全连接层2（fully connected layer)====
W_fc2=weight_Variables([1024,10]) #10个类别
b_fc2=bias_Variable([10])
#分类结果
y=tf.matmul(h_fc1_drop,W_fc2)+b_fc2

#6 loss and optimizer
loss=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=ys,logits=y))
optimizer=tf.train.AdamOptimizer(1e-4).minimize(loss)

#7 启动会话
sess=tf.InteractiveSession()
sess.run(tf.global_variables_initializer())

#8 training and test
for i in range(1000):
     # 100 data points are randomly selected from the training data set
    batch_x, batch_y=mnist.train.next_batch(100)
    #training
    sess.run(optimizer,feed_dict={xs:batch_x, ys:batch_y,keep_pro:0.5})
    if i%50==0:
        print(compute_accuracy(mnist.test.images, mnist.test.labels))

4 输出结果

0.0947 0.8033 0.8809 0.9039 0.9223 0.9276 0.941 0.9473 0.9492 0.9496 0.9556
0.9574 0.9586 0.9622 0.965 0.9654 0.9668 0.9679 0.9709 0.9689    

        可以看出在前几次训练时，测试精度大幅提高，最高达到97.09%，而也不是训练的次数越多越好，相比于之前只用softmax分类器进行识别，测试精度提高了约10%。