简体繁体 English

基本的 deeplearning4j 分类示例

[英]Basic deeplearning4j classification example

原文 2020-01-26 22:31:47 5 1 java/ neural-network/ classification/ deeplearning4j/ encog

I need a very basic classification or similar example for deeplearning4j framework.我需要一个非常基本的分类或 deeplearning4j 框架的类似示例。

I have the classic training set in form of pairs of already normalized double arrays [0.01, 0.45, 0.0, ....] -> [0.0, 0.1, 0.0, 0.0, ...] and need to:我有一对已经标准化的双数组形式的经典训练集 [0.01, 0.45, 0.0, ....] -> [0.0, 0.1, 0.0, 0.0, ...] 并且需要：

Build and train a simple feedforward neural network with N hidden layers构建和训练一个带有 N 个隐藏层的简单前馈神经网络
Feed a set of uncategorized double arrays to trained network and get a set of output vectors将一组未分类的双数组馈送到训练网络并获得一组输出向量

Could somebody please share a basic and short example that does this?有人可以分享一个基本而简短的例子吗？

UPD: Something like this but for deeplearning4j would really help. UPD：像这样的东西，但对于 deeplearning4j 真的会有帮助。

1 个解决方案

Take a look at this example which shows how to train a nn on an XOR relationship.看看这个例子，它展示了如何在 XOR 关系上训练 nn。 First you have to convert your doubles into ndarrays.首先，您必须将双打转换为 ndarrays。 To do this use the Nd4j.create(...) method.为此，请使用 Nd4j.create(...) 方法。 Then you need to set up a dataset like here .然后你需要像这里一样设置一个数据集。