You've finally got that perfect trained model for your data set. To run and deploy it to production, there's a host of issues that lie ahead. Performance latency, environments, framework compatibility, security, deployment targets…there are lots to consider! In this tutorial, we'll look at solutions for these common challenges using ONNX and related tooling. ONNX (Open Neural Network eXchange), an open-source graduate project under the Linux Foundation LF AI, defines a standard format for machine learning models that enables AI developers to use their frameworks and tools of choice to train, infer and deploy on a variety of hardware targets.

Hundreds of thousands of machine learning experiments are conducted globally every single day. Machine learning engineers and students conducting those experiments use a variety of frameworks like TensorFlow, Keras, PyTorch, and others. These models form the foundation of every AI-powered product. So where and how does the ONNX library fit into Machine Learning? What is it exactly, and why did big names like Microsoft and Facebook introduce this library?

Before I begin, let me tell you that this post is part of the Microsoft Student Partners Developer Stories initiative, and is based on the AI and ML Track. We will be exploring various Azure services - Azure Notebooks, Machine Learning Service, Container Instances and Container Registry. This post is beginner-friendly and can be used by anyone to deploy their machine learning models to Azure in a Standard format. Even high school kids are creating Machine Learning models these days, using popular machine learning frameworks like Keras, PyTorch, Caffe, etc. The model format created in one framework slightly differs with the model format created in the other.

The Linux Foundation today announced that ONNX, the open format that makes machine learning models more portable, is now a graduate-level project inside of the organization's AI Foundation. ONNX was originally developed and open-sourced by Microsoft and Facebook in 2017 and has since become somewhat of a standard, with companies ranging from AWS to AMD, ARM, Baudi, HPE, IBM, Nvidia and Qualcomm supporting it. In total, more than 30 companies now contribute to the ONNX code base. It's worth noting that only the ONNX format is included here, not the ONNX runtime, which Microsoft open-sourced a year ago. The runtime is an inference engine for models in the ONNX format and I wouldn't be surprised if, at some point, Microsoft put that under the guidance of a foundation, too… but for now, that's not the case.

Today we will discuss how to launch semantic segmentation and style transfer models in your browser using Tensorflow.js and ONNX.js. The purpose of this article is to determine if relatively large models can be used in a browser on your PC and mobile device. TensorFlow.js is a library for machine learning in JavaScript. It allows us to run existing models or train your own in the browser. The current version of Tensorflow.js, 1.2.7, supports quite a wide range of operations, while most of them are almost the same as in Tensorflow, others such as tf.browser.fromPixels

Two months ago, at //Build 2018, we released ML.NET 0.1, a cross-platform, open source machine learning framework for .NET developers. We've gotten great feedback so far and would like to thank the community for your engagement as we continue to develop ML.NET together in the open. We are happy to announce the latest version: ML.NET 0.3. This release supports exporting models to the ONNX format, enables creating new types of models with Factorization Machines, LightGBM, Ensembles, and LightLDA, and addressing a variety of issues and feedback we received from the community. The main highlights of ML.NET 0.3 release are explained below.