weixin_41138872
weixin_41138872
2018-04-13 07:14
采纳率: 66.7%
浏览 4.9k

softmax分类器,分类概率都是nan是怎么回事?

训练结果有测试集和训练集的准确率,但是调取测试集的预测值时,全都是nan,我需要得到测试结果实际应用的。请问怎么解决?拿一个二分类为例
以下是前期搭建框架
import numpy as np
import tensorflow as tf
x=tf.placeholder("float", [None,115])
y=tf.placeholder("float", [None,2])
W=tf.Variable(tf.zeros([115,2]))
b=tf.Variable(tf.zeros([2]))

actv= tf.nn.softmax(tf.matmul(x,W)+b)
####网上查到说下面这个loss函数中如果是log(0)的话就会有nan,但那应该连训练结果都没有才对吧?我现在能得到训练结果,但是结果都是nan怎么办?
cost=tf.reduce_mean(-tf.reduce_sum(y*tf.log(actv), reduction_indices=1))
learning_rate=0.01
optm= tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
pred=tf.equal(tf.argmax(actv, 1), tf.argmax(y, 1))
accr=tf.reduce_mean(tf.cast(pred,"float"))
init=tf.global_variables_initializer()
sess=tf.InteractiveSession()
sess=tf.Session()
sess.run(init)
training_lenth=len(G)####(回测长度)
training_epochs =50 #训练次数
batch_size = len(G) #每次迭代用多少样本(用全套)
##display_step = 5 #展示
print('Down')

训练重点来了,我需要得到result的实际结果
lenth=2
for epoch in range(training_epochs):
avg_cost=0
num_batch=int(len(G)/batch_size)
for i in range((lenth-1),lenth):
batch_xs=np.array(G[i])
batch_ys=np.array(F[i])
sess.run(optm, feed_dict={x: batch_xs, y: batch_ys})
feeds={x:batch_xs, y: batch_ys}
avg_cost += sess.run (cost, feed_dict=feeds)/(num_batch*lenth)
feeds_train = {x: batch_xs, y: batch_ys}
feeds_test = {x: G[i+1], y: F[i+1]}
train_acc = sess.run(accr, feed_dict=feeds_train) #feed_dict 针对place holder占位
test_acc = sess.run(accr,feed_dict=feeds_test)
result=sess.run(actv,feed_dict=feeds_test)

但是实际给我的结果中,test_acc和train_acc都是有的,但是具体分类的概率值都是nan。
result=sess.run(actv,feed_dict=feeds_train)
print (train_acc)#
print(test_acc)
train_acc
a=sess.run([accr,actv],feed_dict=feeds_test)
print(a)

0.930233
0.465116
[0.46511629, array([[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan],
[ nan, nan]], dtype=float32)]

求大神指教,跪送分

  • 点赞
  • 写回答
  • 关注问题
  • 收藏
  • 邀请回答

3条回答 默认 最新

  • roguesir
    roguesir 2018-04-13 07:39
    已采纳

    你的测试准确率有问题,还不如随机分类的准确率,你在看一下。
    出现nan的原因可能是:真是label为[1,0],预测的label是[0,1],这样反向传播的weight和bias会无穷大,可能的解决办法:
    1、对输入数据进行归一化处理,如将输入的图片数据除以255将其转化成0-1之间的数据;
    2、对于层数较多的情况,各层都做batch_nomorlization;
    3、对设置Weights权重使用tf.truncated_normal(0, 0.01, [3,3,1,64])生成,同时值的均值为0,方差要小一些;
    4、激活函数可以使用tanh;
    5、减小学习率lr。

    点赞 评论
  • weixin_41138872
    weixin_41138872 2018-04-16 01:01

    应该不是概率太低的原因啊,我就编了一层神经网络模型,下面这个例子就是,训练和测试概率都90%多,给出的结果也还是nan
    print(test_acc)
    print(train_acc)

    result=sess.run(actv,feed_dict=feeds_test)
    print(result)

    0.976744
    0.906977
    [[ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]
    [ nan nan]]

    点赞 评论
  • weixin_53132257
    weixin_53132257 2021-03-02 12:48

    请问博主这个事解决了吗 我也遇到了相同的问题

    点赞 评论

相关推荐