Tensorflow_v1学习笔记五 classification

分类问题 手写字识别
28*28的输入 10的输出
mnist自己下载 另外需要下载input_data的代码

1 激活函数：softmax

2 loss：交叉熵

3 代码

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import tensorflow.compat.v1 as tf #使用tf的v1版本
tf.disable_v2_behavior() #使用tf的v1版本
import numpy as np
import matplotlib.pyplot as plt
import input_data

#old_v = tf.logging.get_verbosity()
#tf.logging.set_verbosity(tf.logging.ERROR)
#from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
#tf.logging.set_verbosity(old_v)


def add_layer(inputs,in_size,out_size,activation_function=None):
    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,ys:v_ys})
    corrent_pre=tf.equal(tf.argmax(y_pre,1),tf.argmax(v_ys,1))
    accuracy=tf.reduce_mean(tf.cast(corrent_pre,tf.float32))
    result=sess.run(accuracy,feed_dict={xs:v_xs,ys:v_ys})
    return result

xs = tf.placeholder(tf.float32, [None,784])     #28*28 所以是784个维度
ys = tf.placeholder(tf.float32, [None,10])     # 结果有10种 

prediction=add_layer(xs,784,10,activation_function=tf.nn.softmax)
cross_entropy=tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction),reduction_indices=[1]))

train_step=tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

sess=tf.Session()
sess.run(tf.global_variables_initializer() )

for i in range(1000):
    batch_xs,batch_ys=mnist.train.next_batch(100) #100个100个来学习
    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))