Fork me on GitHub

MNIST数据集入门Demo

发表于 | 分类于
字数统计: 418 | 阅读时长 ≈ 2 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
#Classficiation分类学习
#author:victor

#MNIST数据集入门
from __future__ import print_function
import tensorflow as tf

# number 1 to 10 data
#use mnist data
#使用这两句，会在程序储存的位置出现文件夹MINIST_data
#下载MNIST数据集中的四个压缩包，并放在MINIST_data文件夹中，不要解压
#官网下载地址：http://yann.lecun.com/exdb/mnist/
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data/', one_hot=True)

#define add_layer function
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


#define compute_accuracy function
def compute_accuracy(v_xs, v_ys):
    global prediction
    y_pre = sess.run(prediction, feed_dict={xs: v_xs})
    correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys})
    #output result which is the percent，this percent too high,the prediction too accurate
    return result

# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 784]) # 28x28,也就是有784个数据点
ys = tf.placeholder(tf.float32, [None, 10])#有10个输出

# add output layer
prediction = add_layer(xs, 784, 10,  activation_function=tf.nn.softmax)

# the error between prediction and real data
#分类的话，用softmax配上cross_entropy(交叉熵)
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
                                              reduction_indices=[1]))# loss
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)

#display the graph
for i in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    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))

运行效果

MNIST data result

可以看出图片识别分类的精确度并不是很高，后续用到了CNN卷积神经网络，精确度可以达到99%