Tensorflow函数：tf.nn.softmax_cross_entropy_with_logits 讲解
来源：互联网 发布：数据库基础 编辑：程序博客网 时间：2024/05/04 15:28
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).
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-8import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_datamnist = 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 resultdef 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 networkxs=tf.placeholder(tf.float32,[None,784])/255ys=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。
1 0
- Tensorflow函数：tf.nn.softmax_cross_entropy_with_logits 讲解
- TensorFlow中的tf.nn.softmax_cross_entropy_with_logits 交叉熵 损失函数
- 【TensorFlow】tf.nn.softmax_cross_entropy_with_logits的用法
- 【TensorFlow】tf.nn.softmax_cross_entropy_with_logits的用法
- TensorFlow 介绍 tf.nn.softmax_cross_entropy_with_logits 的用法
- TensorFlow学习---tf.nn.softmax_cross_entropy_with_logits的用法
- tensorflow学习：tf.nn.softmax_cross_entropy_with_logits（）
- 【TensorFlow】tf.nn.softmax_cross_entropy_with_logits的用法
- 【TensorFlow】tf.nn.softmax_cross_entropy_with_logits的用法
- 【TensorFlow】tf.nn.softmax_cross_entropy_with_logits的用法
- tensorflow源码 tf.nn.softmax_cross_entropy_with_logits & tf.nn.sparse_softmax_cross_entropy_with_log
- 对比两个函数tf.nn.softmax_cross_entropy_with_logits和tf.nn.sparse_softmax_cross_entropy_with_logits
- tf.nn.softmax_cross_entropy_with_logits
- tf.nn.softmax_cross_entropy_with_logits()
- tf.nn.softmax_cross_entropy_with_logits
- tf.nn.softmax_cross_entropy_with_logits
- TensorFlow学习笔记之tf.nn.softmax()与tf.nn.softmax_cross_entropy_with_logits的用法
- TensorFlow-tf.nn.conv2d 函数
- 数据结构-选择排序-树形选择排序
- Mybstis XML配置
- xmlhttp的onreadystatechange为什么在send前面
- 反射
- [Easy Connect Naming] 登录ORACLE
- Tensorflow函数：tf.nn.softmax_cross_entropy_with_logits 讲解
- DataFrame的reset_index函数
- MFC不同对话框使用公共数据的几种方法
- Windows10下python2.7安装wxpython
- request.getParameter() 和request.getAttribute() 区别
- ubuntu ssh 连接慢
- xp 无法定位程序输入点 _wfopen_s 于动态链接库 msvcrt.dll 上
- 前端学习笔记，HTML常用标签02
- [BZOJ3033]太鼓达人（欧拉图+dfs）
