深度学习之tensor__MNIST数据集分类简单版本

非解释版算法

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 = 100

n_batch = mnist.train.num_examples // batch_size


x = tf.placeholder(tf.float32,[None,784])
y = tf.placeholder(tf.float32,[None,10])


W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
prediction = tf.nn.softmax(tf.matmul(x,W)+b)

loss = tf.reduce_mean(tf.square(y-prediction))

train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)

init = tf.global_variables_initializer()


correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))

accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

with tf.Session() as sess:
    sess.run(init)
    for epoch in range(21):
        for batch in range(n_batch):
            batch_xs,batch_ys =  mnist.train.next_batch(batch_size)
            sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys})
        
        acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels})
        print("Iter " + str(epoch) + ",Testing Accuracy " + str(acc))

解释版算法

张量的定义
tf.argmax()解析
使用mnist.train.next_batch来实现随机梯度下降

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

#载入数据集
mnist = input_data.read_data_sets("MNIST_data",one_hot=True)

#每个批次的大小
batch_size = 100
#计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size

#定义两个placeholder
x = tf.placeholder(tf.float32,[None,784])
y = tf.placeholder(tf.float32,[None,10])

#创建一个简单的神经网络
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
prediction = tf.nn.softmax(tf.matmul(x,W)+b)

#二次代价函数
loss = tf.reduce_mean(tf.square(y-prediction))
#使用梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)

#初始化变量
init = tf.global_variables_initializer()

#结果存放在一个布尔型列表中
#tf.equal返回是True或False
#argmax返回一维张量中最大的值所在的位置
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))
#求准确率，tf.cast(...)是将True和False转化为1和0
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

with tf.Session() as sess:
    sess.run(init)
    for epoch in range(21):
        for batch in range(n_batch):
            batch_xs,batch_ys =  mnist.train.next_batch(batch_size)
            sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys})
        
        acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels})
        print("Iter " + str(epoch) + ",Testing Accuracy " + str(acc))

优化算法入口

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

mnist = input_data.read_data_sets('MNIST_data',one_hot=True)
#提升算法精确度的第一个入口,batch_size缩小10倍，acc越上升0.015
batch_size = 100
n_batch = mnist.train.num_examples//batch_size

x = tf.placeholder(tf.float32,[None,784])
y = tf.placeholder(tf.float32,[None,10])
#定义隐藏层是第二个入口
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
prediction = tf.nn.softmax(tf.matmul(x,W)+b)

#学习率0.2是提升的第三个入口，变为0.5约上升0.008
loss = tf.reduce_mean(tf.square(y-prediction))
train_step = tf.compat.v1.train.GradientDescentOptimizer(0.2).minimize(loss)

init = tf.compat.v1.global_variables_initializer()
corrent_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))

accuracy = tf.reduce_mean(tf.cast(corrent_prediction,tf.float32))

with tf.Session() as sess:
    sess.run(init)
    #循环epoch是第四个入口，21变为41约上升0.0056
    for epoch in range(21):
        for batch in range(n_batch):
            batch_xs,batch_ys = mnist.train.next_batch(batch_size)
            sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys})
            
        acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels})
        print('Iter '+str(epoch)+',Testing Accuracy: '+str(acc))