简体繁体 English

如何在使用 Keras 的机器学习中使用单个 class 教授 model？

[英]How can I teach a model using single class in machine learning using Keras?

原文 2020-04-04 03:26:11 8 1 python/ machine-learning/ keras

I am new to machine learning and currently got a good start in binary and multi-class model development using Keras.我是机器学习的新手，目前在使用 Keras 进行二进制和多类 model 开发方面有了一个良好的开端。 Now I would like to learn how I could teach a model for outlier image detection.现在我想了解如何教 model 进行异常图像检测。 I used the binary classification method to teach the outlier class by separating the outlier class from other image class.我使用二进制分类方法通过将异常值 class 与其他图像 class 分开来教异常值 class。 This method does not work as soon as I give an image that was not during teaching and the outcome is totally unpredictable.一旦我给出了一个不在教学过程中的图像，这种方法就不起作用，结果完全无法预测。

Where should I start this?我应该从哪里开始？
Is there any online tutorial(s) I could follow?有没有我可以学习的在线教程？

1 个解决方案

There isn't such a thing as single-class classification.不存在单类分类之类的东西。 Your problem is binary since you are differentiating between two classes (normal, outlier).您的问题是二元的，因为您要区分两个类（正常、异常值）。

Having said that, your problem might be too little data for the outliers.话虽如此，您的问题可能是异常值的数据太少。 Unbalanced classes might not produce good results so you should try that first.不平衡的类可能不会产生好的结果，所以你应该先尝试一下。 The second problem might be the model's parameters not having the right values, this requires some experimentation on your part.第二个问题可能是模型的参数没有正确的值，这需要您进行一些实验。

I can't say much since the problem is so vague.我不能说太多，因为这个问题太模糊了。 If you want to post some code and some results I could tell more.如果您想发布一些代码和一些结果，我可以告诉更多。