[英]classify the units in Deep learning for image classification
Suppose we have a database with 10 classes, and we do classification test on it by Deep Belief Network or Convolutional Neural Network. 假设我们有一个包含10个类的数据库,并通过Deep Belief网络或卷积神经网络对其进行分类测试。 The question is that how we can understand which neurons in the last layer are related to which object?
问题是我们如何才能理解最后一层中的哪些神经元与哪个对象有关? In one of the post, a person wrote " to understand which neurons are for an object like shoes and which ones are not you will put that all units in the last layer to another supervised classifier(this can be anything like multi-class-SVM or a soft-max-layer). I do not know how it should be done? I do need more expansion.
在其中一篇文章中,一个人写了“以了解哪些神经元是用于鞋子等对象的,哪些不是,您将把最后一层中的所有单元放到另一个监督的分类器中(这可以是多类SVM之类的东西或soft-max-layer),我不知道应该怎么做?我确实需要更多扩展。
If you have 10 classes, make your last layer have 10 neurons and use the softmax activation function. 如果您有10个类别,请使您的最后一层具有10个神经元,并使用softmax激活功能。 This will make sure that they all lie between 0 and 1 and add up to 1. Then, simply use the index of the neuron with the largest value as your output class.
这样可以确保它们都在0到1之间并且加起来等于1。然后,只需使用具有最大值的神经元的索引作为输出类即可。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.