Tensorflow神经网络
1. 使用交叉上代替二次代价函数
# 定义交叉商代价函数
loss =tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
* 和二次代价函数比较
- 迭代速度块
- 准确率提高了1%左右
* 原因
* 二次代价函数，求导如下
- 交叉熵代价函数，求导如下
* 结论
- 输出神经元是线性，这二次代价函数是合适的旋转 * 输出神经元是Ｓ型函数，则交叉熵合适
2. 过拟合
* 解决方式
- 增加数据集
- 正则化的方法
- Dropout
* dropout
- 使用后，收敛速度变慢
- 使用test数据集和train数据集，dropout解决过拟合
#!/usr/bin/python2.7
# -*- coding: UTF-8 -*-
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import numpy as np
import matplotlib.pyplot as plt
# 载入数据
mnist = input_data.read_data_sets("MNIST_data",one_hot=True)
# 定义批次大小
batch_size=100
#计算批次个数
n_batch=mnist.train.num_examples // batch_size
# 定义placeholder
x=tf.placeholder(tf.float32,[None,784]) # None和batch_size关联
y=tf.placeholder(tf.float32,[None,10])
keep_prob=tf.placeholder(tf.float32)
#创建一个简单的神经网络
W1 = tf.Variable(tf.truncated_normal([784,2000],stddev=0.1))
b1 = tf.Variable(tf.zeros([2000])+0.1)
L1 = tf.nn.tanh(tf.matmul(x,W1)+b1)
L1_drop = tf.nn.dropout(L1,keep_prob)
W2 = tf.Variable(tf.truncated_normal([2000,2000],stddev=0.1))
b2 = tf.Variable(tf.zeros([2000])+0.1)
L2 = tf.nn.tanh(tf.matmul(L1_drop,W2)+b2)
L2_drop = tf.nn.dropout(L2,keep_prob)
W3 = tf.Variable(tf.truncated_normal([2000,1000],stddev=0.1))
b3 = tf.Variable(tf.zeros([1000])+0.1)
L3 = tf.nn.tanh(tf.matmul(L2_drop,W3)+b3)
L3_drop = tf.nn.dropout(L3,keep_prob)
W4 = tf.Variable(tf.truncated_normal([1000,10],stddev=0.1))
b4 = tf.Variable(tf.zeros([10])+0.1)
prediction = tf.nn.softmax(tf.matmul(L3_drop,W4)+b4)
# 定义交叉商代价函数
loss =tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
#使用梯度下降算法
train_step=tf.train.GradientDescentOptimizer(0.2).minimize(loss)
# 初始化变量
init=tf.global_variables_initializer()
# 结果存放在bool列表
correct_prediction=tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))
#求准确吕
accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
with tf.Session() as sess:
sess.run(init)
for epoch in range(31): #所有图片训练21次
for bacth 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,keep_prob:0.7}) #1.0是dropout无作用,全部连接
test_acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0}) #测试集的数据
train_acc = sess.run(accuracy, feed_dict={x: mnist.train.images, y: mnist.train.labels, keep_prob: 1.0})
print("Iter " + str(epoch) + ",Testing Accuracy " + str(test_acc) + ",Training Accuracy " + str(train_acc))
3 优化器
* Tensorflow的优化器
* adadekle速度最快，然后是adegrad和RMSprop，SGD速度慢
* SGD准确度高
#使用梯度下降算法
# train_step=tf.train.GradientDescentOptimizer(0.2).minimize(loss)
train_step=tf.train.AdamOptimizer(1e-2).minimize(loss)