TensorFlow训练神经网络cost一直为0
问题描述
这几天在用TensorFlow搭建一个神经网络来做一个binary classifier,搭建一个典型的神经网络的基本思路是:
- 定义神经网络的layers(层)以及初始化每一层的参数
- 然后迭代:
- 前向传播(Forward propagation)
- 计算cost(Compute cost)
- 反向传播(Backward propagation)
- 更新参数(Update parameters)
- 使用训练好的参数去做预测
在训练的时候发现了一个很奇怪的现象:每一次迭代所有的cost都为0。一开始以为是参数初始化出了问题,花了好多时间在上面。后来仔细研究了一下发现是最后一层的输出函数用错了,我用的是tf.nn.softmax_cross_entropy_with_logits来计算cost。 我们知道softmax一般是用来做multiclass classifier的,也就是输出的类别要大于两个。对于一个binary classifier而言,很明显我们要用sigmoid函数也就是tf.nn.sigmoid_cross_entropy_with_logits来计算cost,于是问题解决。
为什么?
那么为什么在binary classifier中使用了softmax之后cost就一直是0呢?我们先来看一下softmax的公式:
s(z)j=ezj∑Kk=1ezks(z)j=ezj∑k=1Kezk
- binary classifier的output是一维的(one-dimension 0/1),那么如果只有一个元素,那么s(z)就永远等于1,不管z的值是多少。
- 恒定输出1之后,我们结合交叉熵的计算公式可知:
- 如果true label是0,那么
-0*log(1) = 0 - 如果true label是1,那么
-1*log(1) = 0
- 如果true label是0,那么
Tensorflow函数:tf.nn.softmax_cross_entropy_with_logits 讲解
首先把Tensorflow英文API搬过来:
tf.nn.softmax_cross_entropy_with_logits(_sentinel=None, labels=None, logits=None, dim=-1, name=None)
Computes softmax cross entropy between logits and labels.
Measures the probability error in discrete classification tasks in which the classes are mutually exclusive (each entry is in exactly one class). For example, each CIFAR-10 image is labeled with one and only one label: an image can be a dog or a truck, but not both.
NOTE: While the classes are mutually exclusive, their probabilities need not be. All that is required is that each row oflabels is a valid probability distribution. If they are not, the computation of the gradient will be incorrect.
If using exclusive labels (wherein one and only one class is true at a time), seesparse_softmax_cross_entropy_with_logits.
WARNING: This op expects unscaled logits, since it performs a softmax on logits internally for efficiency. Do not call this op with the output of softmax, as it will produce incorrect results.
logits and labels must have the same shape [batch_size, num_classes] and the same dtype (either float16,float32, or float64).
Note that to avoid confusion, it is required to pass only named arguments to this function.
Args:
_sentinel: Used to prevent positional parameters. Internal, do not use.labels: Each rowlabels[i]must be a valid probability distribution.logits: Unscaled log probabilities.dim: The class dimension. Defaulted to -1 which is the last dimension.name: A name for the operation (optional).
这个函数至少需要两个参数:labels, logits.
labels:为神经网络期望的输出
logits:为神经网络最后一层的输出
警告:这个函数内部自动计算softmax,然后再计算交叉熵代价函数,也就是说logits必须是没有经过tf.nn.softmax函数处理的数据,否则导致训练结果有问题。建议编程序时使用这个函数,而不必自己编写交叉熵代价函数。
下面是两层CNN识别mnist的softmax回归实验:
- #coding=utf-8
- import tensorflow as tf
- from tensorflow.examples.tutorials.mnist import input_data
- mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
- def compute_accuracy(v_xs,v_ys):
- global prediction
- y_pre=sess.run(prediction,feed_dict={xs:v_xs,keep_prob:1}) #这里的keep_prob是保留概率,即我们要保留的RELU的结果所占比例
- correct_prediction=tf.equal(tf.argmax(y_pre,1),tf.argmax(v_ys,1))
- accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
- result=sess.run(accuracy,feed_dict={xs:v_xs,ys:v_ys,keep_prob:1})
- return result
- def weight_variable(shape):
- inital=tf.truncated_normal(shape,stddev=0.1) #stddev爲標準差
- return tf.Variable(inital)
- def bias_variable(shape):
- inital=tf.constant(0.1,shape=shape)
- return tf.Variable(inital)
- def conv2d(x,W): #x爲像素值,W爲權值
- #strides[1,x_movement,y_movement,1]
- #must have strides[0]=strides[3]=1
- #padding=????
- return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')#
- def max_pool_2x2(x):
- # strides[1,x_movement,y_movement,1]
- return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')#ksize二三维为池化窗口
- #define placeholder for inputs to network
- xs=tf.placeholder(tf.float32,[None,784])/255
- ys=tf.placeholder(tf.float32,[None,10])
- keep_prob=tf.placeholder(tf.float32)
- x_image=tf.reshape(xs, [-1,28,28,1]) #-1为这个维度不确定,变成一个4维的矩阵,最后为最里面的维数
- #print x_image.shape #最后这个1理解为输入的channel,因为为黑白色所以为1
- ##conv1 layer##
- W_conv1=weight_variable([5,5,1,32]) #patch 5x5,in size 1 是image的厚度,outsize 32 是提取的特征的维数
- b_conv1=bias_variable([32])
- h_conv1=tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1)# output size 28x28x32 因为padding='SAME'
- h_pool1=max_pool_2x2(h_conv1) #output size 14x14x32
- ##conv2 layer##
- W_conv2=weight_variable([5,5,32,64]) #patch 5x5,in size 32 是conv1的厚度,outsize 64 是提取的特征的维数
- b_conv2=bias_variable([64])
- h_conv2=tf.nn.relu(conv2d(h_pool1,W_conv2)+b_conv2)# output size 14x14x64 因为padding='SAME'
- h_pool2=max_pool_2x2(h_conv2) #output size 7x7x64
- ##func1 layer##
- W_fc1=weight_variable([7*7*64,1024])
- b_fc1=bias_variable([1024])
- #[n_samples,7,7,64]->>[n_samples,7*7*64]
- h_pool2_flat=tf.reshape(h_pool2,[-1,7*7*64])
- h_fc1=tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1)+b_fc1)
- h_fc1_drop=tf.nn.dropout(h_fc1,keep_prob) #防止过拟合
- ##func2 layer##
- W_fc2=weight_variable([1024,10])
- b_fc2=bias_variable([10])
- #prediction=tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2)+b_fc2)
- prediction=tf.matmul(h_fc1_drop,W_fc2)+b_fc2
- #h_fc1_drop=tf.nn.dropout(h_fc1,keep_prob) #防止过拟合
- #the errro between prediction and real data
- #cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction),reduction_indices=[1]))
- cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=ys, logits=prediction)
- train_step = tf.train.AdamOptimizer(1e-4).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,keep_prob:0.5})
- if i%50 ==0:
- accuracy = 0
- for j in range(10):
- test_batch = mnist.test.next_batch(1000)
- acc_forone=compute_accuracy(test_batch[0], test_batch[1])
- #print 'once=%f' %(acc_forone)
- accuracy=acc_forone+accuracy
- print '测试结果:batch:%g,准确率:%f' %(i,accuracy/10)
实验结果为:
- 测试结果:batch:0,准确率:0.090000
- 测试结果:batch:50,准确率:0.788600
- 测试结果:batch:100,准确率:0.880200
- 测试结果:batch:150,准确率:0.904600
- 测试结果:batch:200,准确率:0.927500
- 测试结果:batch:250,准确率:0.929800
- 测试结果:batch:300,准确率:0.939600
- 测试结果:batch:350,准确率:0.942100
- 测试结果:batch:400,准确率:0.950600
- 测试结果:batch:450,准确率:0.950700
- 测试结果:batch:500,准确率:0.956700
- 测试结果:batch:550,准确率:0.956000
- 测试结果:batch:600,准确率:0.957100
- 测试结果:batch:650,准确率:0.958400
- 测试结果:batch:700,准确率:0.961500
- 测试结果:batch:750,准确率:0.963800
- 测试结果:batch:800,准确率:0.965000
- 测试结果:batch:850,准确率:0.966300
- 测试结果:batch:900,准确率:0.967800
- 测试结果:batch:950,准确率:0.967700
迭代次数没有太多,否则准确率还会提高。
TensorFlow训练神经网络cost一直为0的更多相关文章
- 吴裕雄 python 神经网络——TensorFlow训练神经网络:不使用滑动平均
import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data INPUT_NODE = 784 ...
- 吴裕雄 python 神经网络——TensorFlow训练神经网络:不使用隐藏层
import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data INPUT_NODE = 784 ...
- 吴裕雄 python 神经网络——TensorFlow训练神经网络:不使用激活函数
import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data INPUT_NODE = 784 ...
- 吴裕雄 python 神经网络——TensorFlow训练神经网络:不使用指数衰减的学习率
import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data INPUT_NODE = 784 ...
- 吴裕雄 python 神经网络——TensorFlow训练神经网络:不使用正则化
import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data INPUT_NODE = 784 ...
- 吴裕雄 python 神经网络——TensorFlow训练神经网络:全模型
import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data INPUT_NODE = 784 ...
- 吴裕雄 python 神经网络——TensorFlow训练神经网络:花瓣识别
import os import glob import os.path import numpy as np import tensorflow as tf from tensorflow.pyth ...
- 吴裕雄 python 神经网络——TensorFlow训练神经网络:MNIST最佳实践
import os import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data INPUT_N ...
- Tensorflow训练神经网络
以下代码摘自<Tensorflow实战Google 深度学习框架>. 由于这段代码包含了激活函数去线性化,多层神经网络,指数衰减学习率,正则化防止过拟合,滑动平均稳定模型等手段,涵盖了神经 ...
随机推荐
- Java基础常见英语词汇(共70个)
——————————ASP.Net+Android+IOS开发..Net培训.期待与您交流!—————————— Java英文单词 OO: object—oriented ,面向对象 OOP:obje ...
- 001 SpringMVC的helloWorld程序
一:helloworld程序 1.结构目录 2.添加lib包 3.在web.xml中配置DispatchServlet 这个就是主servlet. <?xml version="1.0 ...
- Javassist学习总结
今天在弄dubbo时出现了一个依赖缺少问题,就好奇研究一下,这个依赖是啥. javassist是一个字节码类库,可以用他来动态生成类,动态修改类等等 1.介绍Javassist 要想将编译时不存在的类 ...
- shiro xml标准配置
<?xml version="1.0" encoding="UTF-8"?> <beans xmlns="http://www.sp ...
- 【Ray Tracing in One Weekend 超详解】 光线追踪1-9 景深
今天我们来学最后一章 Chapter11:Defocus Blur Preface 散焦模糊 也称 景深 首先,我们来了解一下散焦模糊,我们在真实相机中散焦模糊的原因是因为它们需要一个大圈(而不仅仅是 ...
- Java Object part1
java中Object是所有类的父类,这句话就不多做解释.但是Object中到底有哪些我们常用的方法呢? 1. public native int hashCode(); 这个方法是一个nat ...
- SOAP port
To determine the SOAP port on WebSphere Base: Server Types > WebSphere application servers > [ ...
- 【HDU 5382】 GCD?LCM! (数论、积性函数)
GCD?LCM! Time Limit: 2000/1000 MS (Java/Others) Memory Limit: 131072/131072 K (Java/Others)Total ...
- BZOJ4556 HEOI2016字符串
没错,又是这题,使用后缀自动机,反向建树,主席树维护right集合. By:大奕哥 #include<bits/stdc++.h> using namespace std; ; ]; ch ...
- NOIP2015其余几道题
T1: #include<cstdio> #include<cstring> #include<algorithm> #include<cmath> # ...