如何建立及建立训练用于Core ML的神经模型

本文介绍了如何建立及建立训练用于Core ML的神经模型的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！ 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，如果我想自己创建一个模型怎么办?我该怎么做以及使用哪些工具和工具?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没有提供训练您自己的模型的方法.您只能将现有的转换为Apple的"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还与 Scikit学习 *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.

您还可以在不使用Core ML的iOS上训练和运行神经网络，只需使用 Caffe 2 或 TensorFlow .我支持与iOS兼容的机器学习库的详细列表，如果您有兴趣.

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出色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也兼容，但是scikit-learn仍然在后台使用它.

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