tensorflow学习系列三：多层感知器MLP

    多层感知即至少包含一个隐含层的神经网络，较为典型的就是BP神经网络。本文依旧以mnist数据集进行对MLP进行实验，实验中MLP仅包含了一个隐含层，若想增加更多从层基于该实验拓展也很简单。

# -*- coding: utf-8 -*-
"""
Created on Sat Jun  9 14:37:08 2018

@author: kuangyongjian
"""
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf

mnist = input_data.read_data_sets('MNIST_data/',one_hot = True)

in_units = 784 #输入维度
h1_units = 300 #隐含层维度

#权重和偏置的初始化
W1 = tf.Variable(tf.truncated_normal([in_units,h1_units],stddev = 0.1))
b1 = tf.Variable(tf.zeros([h1_units]))
W2 = tf.Variable(tf.zeros([h1_units,10]))
b2 = tf.Variable(tf.zeros([10]))

#定义计算图的输入
x = tf.placeholder(tf.float32,[None,in_units])
y_ = tf.placeholder(tf.float32,[None,10])
keep_prob = tf.placeholder(tf.float32)

#定义模型结构(网络的前向过程)
hidden1 = tf.nn.relu(tf.matmul(x,W1) + b1)
hidden1_drop = tf.nn.dropout(hidden1,keep_prob)
y = tf.nn.softmax(tf.matmul(hidden1_drop,W2) + b2)

#定义损失
loss = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y),reduction_indices = [1]))

#定义优化器
train_step = tf.train.AdadeltaOptimizer(0.3).minimize(loss)

#初始化各个变量
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)

#网络训练
for i in range(10000):
    batch_x,batch_y = mnist.train.next_batch(100)
    train_step.run(session = sess,feed_dict = {x:batch_x,y_:batch_y,keep_prob:0.5})


#模型评估
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
print(accuracy.eval(session = sess,feed_dict = {x:mnist.test.images,y_:mnist.test.labels,keep_prob:1.0}))

如有不当之处，请指教，谢谢！