通过EncogModel节省网络和权重 [英] Saving networks and weights fro EncogModel

问题描述

我能够创建一个网络，对其进行训练并使用EncogModel对其进行评估.但是，我希望能够节省网络，训练和重量，以便每次运行它时都不必进行训练.我发现了encog的持久性，但是我很难将encogmodel和percistence结合在一起.有没有可用的示例代码?如果没有，怎么办?

I was able to create a network, train it and evaluate it using EncogModel. However, i would like to be able to save the network, training and weights, so that every time i run it, i dont have to train it. I found encog persistence, but I'm having a hard time putting encogmodel and percistence together. is there any sample codes available? If not, how could this be done?

推荐答案

已使用:

SerializeObject.Save(string path, network);

和

EncogUtility.SaveEGB( FileInfo path , data);

EncogDirectoryPersistance.SaveObject(FileInfo f,network)似乎不支持NEAT，它一直返回错误.

EncogDirectoryPersistance.SaveObject(FileInfo f,network) seemed to not support NEAT, it kept returning an error.

这篇关于通过EncogModel节省网络和权重的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！