{"id":12186,"date":"2022-06-06T10:00:00","date_gmt":"2022-06-06T01:00:00","guid":{"rendered":"https:\/\/www.gigas-jp.com\/appnews\/?p=12186"},"modified":"2022-06-06T10:24:43","modified_gmt":"2022-06-06T01:24:43","slug":"what-is-onnx","status":"publish","type":"post","link":"https:\/\/www.gigas-jp.com\/appnews\/archives\/12186","title":{"rendered":"What is ONNX"},"content":{"rendered":"\n

ONNX is a machine learning framework which acts like a medium to convert between different machine learning frameworks.<\/p>\n\n\n\n

\"Image\"
Credit : LF AI & Data Foundation<\/figcaption><\/figure>\n\n\n\n

ONNX is designed to enable framework interoperability. There are many great machine learning libraries in multiple languages \u2014 PyTorch, TensorFlow, MXNet, and Caffe are just a few of the most popular ones in recent years, but there are many others.
The idea is that you can use one stack of tools to train your model and use another for inference and prediction to expand your model.<\/p>\n\n\n\n

For example, once you’ve trained your model, you need to deploy it to a new iOS app so that anyone with a previously trained model can see the safety of their food. I first trained my model with PyTorch, but iOS expects to use CoreML for use within the app. ONNX is an intermediate representation of the model that allows you to easily move from one environment to another.<\/p>\n\n\n\n

With tools such as ONNX-CoreML, you can now easily convert pre-trained models to files, import them into XCode, and integrate them seamlessly with your application.<\/p>\n\n\n\n

This is just an overview of what ONNX is about. I will talk more detail in future.<\/p>\n\n\n\n

Yuuma<\/p>\n

\n
<\/g:plusone><\/div>\n
\"\u3053\u306e\u30a8\u30f3\u30c8\u30ea\u30fc\u3092\u306f\u3066\u306a\u30d6\u30c3\u30af\u30de\u30fc\u30af\u306b\u8ffd\u52a0\"<\/a>