标签：数据 open 视频 部分 square .sh func weight odi
内容总结与莫烦的视频。
这里多层感知器代码写的是一个简单的三层神经网络，输入层，隐藏层，输出层。代码的目的是你和一个二次曲线。同时，为了保证数据的自然，添加了mean为0，steddv为0.05的噪声。
添加层代码：
def addLayer(inputs,inSize,outSize,activ_func = None):#insize outsize表示输如输出层的大小，inputs是输入。activ_func是激活函数，输出层没有激活函数。默认激活函数为空 with tf.name_scope(name = "layer"): with tf.name_scope("weigths"): Weights = tf.Variable(tf.random_normal([inSize,outSize]),name = "W") bias = tf.Variable(tf.zeros([1,outSize]),name = "bias") W_plus_b = tf.matmul(inputs,Weights)+bias if activ_func == None: return W_plus_b else: return activ_func(W_plus_b)
输入：
1 with tf.name_scope(name = "inputs"):#with这个主要是用来在tensorboard上显示用。 2 xs = tf.placeholder(tf.float32,[None,1],name = "x_input")#不是-1哦 3 ys = tf.placeholder(tf.float32,[None,1],name = "y_input") 4 l1 = addLayer(xs,1,10,activ_func= tf.nn.relu) 5 y_pre = addLayer(l1,10,1,activ_func=None)
其他部分：
需要注意的是
1 with tf.name_scope("loss"): 2 loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-y_pre), 3 reduction_indices=[1]))#这里reduction_indices=[1]类似于numpy中的那种用法，是指横向还是竖向，reduce_sum函数貌似主要是用于矩阵的，向量可以不使用 4 with tf.name_scope("train"): 5 train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss) 6 #在以后的版本中，这里的initialize_all_variable()可能被逐步抛弃使用global_variable_init（大概是这么写的）那个函数。欢迎指正。 7 init = tf.initialize_all_variables()#init这一步很重要，在训练前一定要是使用sess.run(init)操作（只要是你用到了Variable） 8 writer = tf.summary.FileWriter("logs/",sess.graph) 9 with tf.Session() as sess: 10 11 sess.run(init) 12 13 for i in range(1000): 14 sess.run(train_step,feed_dict = {xs:x_data,ys:y_data}) 15 if i % 50 == 0: 16 print(sess.run(loss,feed_dict = {xs:x_data,ys:y_data}))#只要是你的操作中有涉及到placeholder一定要记得使用feed_dict
所有代码：
1 # -*- coding: utf-8 -*- 2 """ 3 Created on Tue Jun 13 15:41:23 2017 4 5 @author: Jarvis 6 """ 7 8 import tensorflow as tf 9 import numpy as np 10 11 def addLayer(inputs,inSize,outSize,activ_func = None): 12 with tf.name_scope(name = "layer"): 13 with tf.name_scope("weigths"): 14 Weights = tf.Variable(tf.random_normal([inSize,outSize]),name = "W") 15 bias = tf.Variable(tf.zeros([1,outSize]),name = "bias") 16 W_plus_b = tf.matmul(inputs,Weights)+bias 17 if activ_func == None: 18 return W_plus_b 19 else: 20 return activ_func(W_plus_b) 21 x_data = np.linspace(-1,1,300)[:,np.newaxis] 22 noise = np.random.normal(0,0.05,x_data.shape) 23 y_data = np.square(x_data)-0.5+noise 24 25 with tf.name_scope(name = "inputs"): 26 xs = tf.placeholder(tf.float32,[None,1],name = "x_input")#不是-1哦 27 ys = tf.placeholder(tf.float32,[None,1],name = "y_input") 28 l1 = addLayer(xs,1,10,activ_func= tf.nn.relu) 29 y_pre = addLayer(l1,10,1,activ_func=None) 30 with tf.name_scope("loss"): 31 loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-y_pre), 32 reduction_indices=[1])) 33 with tf.name_scope("train"): 34 train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss) 35 36 init = tf.initialize_all_variables() 37 writer = tf.summary.FileWriter("logs/",sess.graph) 38 with tf.Session() as sess: 39 40 sess.run(init) 41 42 for i in range(1000): 43 sess.run(train_step,feed_dict = {xs:x_data,ys:y_data}) 44 if i % 50 == 0: 45 print(sess.run(loss,feed_dict = {xs:x_data,ys:y_data}))
标签：数据 open 视频 部分 square .sh func weight odi
原文地址：http://www.cnblogs.com/silence-tommy/p/7039702.html
