如何创建 &训练一个用于 Core ML 的神经模型 [英] How to create & train a neural model to use for Core ML

问题描述

Apple 推出了 Core ML.有许多第三方提供经过训练的模型.

Apple introduced Core ML. There are many third parties providing trained models.

但是如果我想自己创建模型怎么办?我怎样才能做到这一点以及使用什么工具和工具?我可以使用哪些技术?

But what if I want to create a model myself? How can I do that and what tools & technologies can I use?

推荐答案

Core ML 不提供训练您自己的模型的方法.您只能将现有格式转换为 Apple 'mlmodel' 格式.

Core ML doesn't provide a way to train your own models. You only can convert existing ones to Apple 'mlmodel' format.

要创建您自己的神经网络，请使用 Caffe 或 Keras 框架，然后将这些模型转换为 CoreML 格式.对于传统的机器学习算法，Core ML 还兼容 Scikit-learn* 和 XGBoost.

To create your own neural networks, use Caffe or Keras frameworks and then convert those models to CoreML format. For traditional machine learning algorithms Core ML is also compatible with Scikit-learn* and XGBoost.

您也可以在没有 Core ML 的情况下在 iOS 上训练和运行神经网络，只需使用 Caffe 2 或 TensorFlow.我支持 一长串与 iOS 兼容的机器学习库，如果你有兴趣.

You can also train and run neural networks on iOS without Core ML, just use Caffe 2 or TensorFlow. I support a long list of iOS-compatible machine learning libraries, if you're interested.

上面提到的所有库都有很好的文档和大量教程供您开始创建自己的模型.

All libraries mentioned above have a great documentation and a lot of tutorials for you to start creating your own models.

*LibSVM 也是兼容的，但 scikit-learn 仍然在幕后使用它.

*LibSVM is also compatible, but scikit-learn uses it under the hood anyway.

这篇关于如何创建 &训练一个用于 Core ML 的神经模型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！