[CppDay20] Interoperable AI: ONNX & ONNXRuntime in C++ (M. Arena, M.Verasani)

---
ONNX is an open source format built to represent machine learning and deep learning models. The project enables AI developers to use models with a variety of frameworks, tools, runtimes, and compilers. The development of ONNX is driven by a community of partners including Microsoft, Facebook, NVIDIA and Mathworks.

ONNXRuntime is an open source project driven by Microsoft which provides an optimized implementation of all the standard ONNX operators for the CPU. It supports a plenty of acceleration targets like cuDNN by NVIDIA and MKL-DNNL by Intel, and it exposes the right abstraction and runtime support for custom accelerators and runtimes.

In this session you’ll learn about ONNX and ONNXRuntime, and see some practical examples of accelerating ONNX models in C++ with ONNXRuntime.