TensorFlow入门：简单的分类任务和overfitting

简单的分类任务:

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2018/5/14 17:20
# @Author  : HJH
# @Site    : 
# @File    : classification.py
# @Software: PyCharm

#利用独热编码one hot来分类手写数字
import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data

def add_layer(input,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(input,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})
    #在独热编码中哪个位置的概率最高即为哪个数
    correct_prediction=tf.equal(tf.argmax(y_pre,1),tf.argmax(v_ys,1))
    #判断这个手写数字的准确率
    accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
    result=sess.run(accuracy,feed_dict={xs:v_xs,ys:v_ys})
    return result


if __name__=='__main__':
    # 若没有该数据，则从网上下载该数据
    mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
    xs=tf.placeholder(tf.float32,[None,784])#28*28
    ys=tf.placeholder(tf.float32,[None,10])

    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)
        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))

使用dropout处理overfitting：

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2018/5/14 20:20
# @Author  : HJH
# @Site    : 
# @File    : overfitting.py
# @Software: PyCharm

import tensorflow as tf
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelBinarizer

def add_layer(input,in_size,out_size,layer_name,activation_function=None):
    global keep_prob
    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(input,Weights)+biases
    #克服过拟合
    Wx_plus_b=tf.nn.dropout(Wx_plus_b,keep_prob)
    if activation_function==None:
        outputs=Wx_plus_b
    else:
        outputs=activation_function(Wx_plus_b)
    tf.summary.histogram(layer_name+'/outputs',outputs)
    return outputs


if __name__=='__main__':
    digits=load_digits()
    X=digits.data
    y=digits.target
    y=LabelBinarizer().fit_transform(y)
    X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=3)

    keep_prob=tf.placeholder(tf.float32)
    xs=tf.placeholder(tf.float32,[None,64])
    ys=tf.placeholder(tf.float32,[None,10])

    l1=add_layer(xs,64,50,'l1',activation_function=tf.nn.tanh)
    prediction = add_layer(l1, 50, 10, 'l2', activation_function=tf.nn.softmax)
    cross_entropy=tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction),reduction_indices=[1]))
    tf.summary.scalar('loss',cross_entropy)
    train_step=tf.train.GradientDescentOptimizer(0.6).minimize(cross_entropy)

    sess=tf.Session()
    merged=tf.summary.merge_all()

    train_writer=tf.summary.FileWriter('logs/train',sess.graph)
    test_wirter=tf.summary.FileWriter('logs/test',sess.graph)

    sess.run(tf.global_variables_initializer())
    for i in range(1000):
        #保持60%的数据不被drop掉的
        sess.run(train_step,feed_dict={xs:X_train,ys:y_train,keep_prob:0.5})
        if i%50==0:
            #记录的时候不需要drop掉
            train_result=sess.run(merged,feed_dict={xs:X_train,ys:y_train,keep_prob:1})
            test_result = sess.run(merged, feed_dict={xs: X_test, ys: y_test,keep_prob:1})
            train_writer.add_summary(train_result,i)
            test_wirter.add_summary(test_result,i)