This post has been republished via RSS; it originally appeared at: Channel 9.
ONNX is a open format to represent deep learning models that is supported by various frameworks and tools. This format makes it easier to interoperate between frameworks and to maximize the reach of your hardware optimization investments
In this episode, Seth Juarez (@sethjuarez) sits with Rich to show us how we can use the ONNX runtime inside of our .NET applications. He gives us a quick introduction to training a model with PyTorch, and also explains some foundational concepts around prediction accuracy.
- [01:01] - Brief overview of training a machine learning model
- [02:54] - PyTorch training in Python
- [07:43] - Understanding accuracy and loss
- [10:50] - What is ONNX ?
- [11:53] - Consuming model with ONNX in .NET
- [25:38] - ML .NET and ONNX
- [26:58] - Industry usage
Useful Links
- ONNX Homepage
- ONNX on GitHub
- ONNX NuGet
- ONNX Runtime is now open source
- PyTorch
- Seth's Pytorch demo on GitHub
