tensorflow 手写体识别的两种实现

神经网络大概的几个步骤
1.获取数据，确定输入的形式
2.定义网络结构，包括权重和偏置的初始化
3.定义目标函数（或者损失函数）
4.定义优化函数（如随机梯度下降，Adam等）
5.会话（Session）Session对象负责着图中所有Op的执行
6 训练训练数据
7.测试集上获取相应的指标的大小（本文是准确率）
8.保存模型

1. 利用神经网络实现手写体识别

import warnings
warnings.filterwarnings('ignore')
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
batch_size = 50
X_holder = tf.placeholder(tf.float32)
y_holder = tf.placeholder(tf.float32)

Weights = tf.Variable(tf.zeros([784, 10]))
biases = tf.Variable(tf.zeros([1,10]))
predict_y = tf.nn.softmax(tf.matmul(X_holder, Weights) + biases)
loss = tf.reduce_mean(-tf.reduce_sum(y_holder * tf.log(predict_y), 1))
optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)

session = tf.Session()
init = tf.global_variables_initializer()
session.run(init)

for i in range(600):
    images, labels = mnist.train.next_batch(batch_size)
    session.run(train, feed_dict={X_holder:images, y_holder:labels})
    if i % 100 == 0:
        correct_prediction = tf.equal(tf.argmax(predict_y, 1), tf.argmax(y_holder, 1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
        accuracy_value = session.run(accuracy, feed_dict={X_holder:mnist.test.images, y_holder:mnist.test.labels})
        print('step:%d  valid accuracy:%.4f' %(i, accuracy_value))

2.利用cnn实现手写体识别

import warnings
warnings.filterwarnings('ignore')
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
x=tf.placeholder(tf.float32,[None,784])
y_=tf.placeholder(tf.float32,[None,10])
x_image=tf.reshape(x,[-1,28,28,1])

def weight_variable(shape):
    initial=tf.truncated_normal(shape,stddev=0.1)
    return tf.Variable(initial)

def bias_variable(shape):
    initial=tf.constant(0.1,shape=shape)
    return tf.Variable(initial)


def conv2d(x,W):
    return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')
def max_pool2x2(x):
    return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')


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_pool2x2(h_conv1)


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_pool2x2(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)

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


w_fc2=weight_variable([1024,10])
b_fc2=bias_variable([10])
y_conv=tf.matmul(h_fc1_drop,w_fc2)+b_fc2

cross_entropy=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_,logits=y_conv))

loss=tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)

correct_predict = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_predict, tf.float32))
init=tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    for i in range(600):
        batch=mnist.train.next_batch(32)

        if i%100==0:
            train_accracy=accuracy.eval(feed_dict={x:batch[0],y_:batch[1],keep_prob:1.0})
            print("第%d,训练集的正确率%.4f" % (i,train_accracy))
        sess.run(loss,feed_dict={x:batch[0],y_:batch[1],keep_prob:0.5})
    testaccracy=accuracy.eval(feed_dict={x:mnist.test.images,y_:mnist.test.labels,keep_prob:1.0})
    print(testaccracy)