[笔记][tf]|[mnist]tensorflow学习笔记(4)

8 篇文章 0 订阅
6 篇文章 0 订阅

[tf]|[mnist]tensorflow学习笔记(4)

参考:莫烦Python: morvanzhou.github.io

往期链接

[笔记]|[tf]|[张量]|[例子1]tensorflow学习笔记(1)
[笔记][tf]|[例子2]tensorflow学习笔记(2)
[笔记]|[tf]|[tensorboard]|[例子2可视化]tensorflow学习笔记(3)
[笔记]|[tf]|[CNN]|[例子3]tensorflow学习笔记(5)
[笔记]|[tf]|[Saver]|[模型的保存与提取]tensorflow学习笔记(6)

使用mnist分类

  • 完整代码:
"""
Please note, this code is only for python 3+. If you are using python 2+, please modify the code accordingly.
"""
from __future__ import print_function
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# number 1 to 10 data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
#下载mnist
def add_layer(inputs, in_size, out_size, activation_function=None,):
    # add one more layer and return the output of this layer
    Weights = tf.Variable(tf.random_normal([in_size, out_size]))
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1,)
    Wx_plus_b = tf.matmul(inputs, Weights) + biases
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b,)
    return outputs

def compute_accuracy(v_xs, v_ys):
    global prediction
    y_pre = sess.run(prediction, feed_dict={xs: v_xs})
    #生成预测值(一行十列(代表0到9)(数值为小数))
    correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1))
    #对比预测值与真实数据的差别返回0与1
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    #计算准确率
    result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys})
    return result

# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 784]) # 28x28
#784个输入
ys = tf.placeholder(tf.float32, [None, 10])
#十个输出
# add output layer
prediction = add_layer(xs, 784, 10,  activation_function=tf.nn.softmax)
#输入784个;输入的数据点有784个;输出10个;激活函数为tf.nn.softmax
#分类学习一般使用tf.nn.softmax
# the error between prediction and real data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
                                              reduction_indices=[1]))  # loss
#tf.nn.softmax配上cross_entropy可生成分类算法
#交叉熵
'''
交叉熵代价函数可以使用sigmod激活函数时,避免因为对sigmod
求导而导致的在一开始的学习缓慢问题
'''
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

sess = tf.Session()
# important step
# tf.initialize_all_variables() no long valid from
# 2017-03-02 if using tensorflow >= 0.12
if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:
    init = tf.initialize_all_variables()
else:
    init = tf.global_variables_initializer()
sess.run(init)

for i in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
#从mnist数据集中提取100个学习(SGD),即:提取出一部分的xs,一部分的ys(学习部分data)
    sess.run(train_step, feed_dict= {xs: batch_xs, ys: batch_ys})
    if i % 50 == 0:
        print(compute_accuracy(
            mnist.test.images, mnist.test.labels))
'''
分为 mnist.train   data与 mnist.test    data
如果使用混合使用,可能会产生人为误差
'''
  • 0
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值