Xavier Geerinck

Enabling Serverless AI with Azure Container Apps and Dapr

AI Model Inferencing with ONNX on GPU (CUDA)

Recently I've been working a lot with different AI Models for a variety of use cases, ranging from simple object classification to massive crowd counting models. While working with these models, I saw that it is always difficult to implement a model in custom code since the Architecture is never included in the weights themselves, thus each model works differently.

Running your AI Workload through Azure Container Apps

For a new project I am working on, I am utilizing a Queuing architecture where jobs come in and a cluster of containers is processing work on this queue. Each job takes an item from a queue, runs the item through its AI pipeline and spits out a JSON response.

Enabling CUDA with PyTorch on Nvidia Jetson and Python 3.9

Parking Garage Sensor implementation using Dapr Actors

The reworked Dapr Javascript SDK has been released a couple of weeks ago! Together with a brand new and easier to use SDK, we have been thinking in the community of reworking the documentation to simplify the examples, more specifically the Actors examples.

Use Bicep and Azure Static Site for your Blog Deployment

Windows Terminal and WSL Tips and Tricks

Did you find yourself ever having to set-up your development environment all the time? Well I did as well! What if I could tell you, you could save many minutes each day by automating this? Enter the world of Windows Terminal and WSL! 😎

Creating an Azure IoT Edge Golden Image

So you are working on a production scale and suddenly notice that you don't have to provision just 1, not 10 but 1000s of devices. What do you do?

Automatically Provision an IoT Device with DPS

Once you get further in the world of the Internet of Things (IoT) you will notice that you have to setup devices in bulk rather than device-per-device. This is where Azure helps you through a service named Device Provisioning Service.

Azure IoT Edge Troubleshooting

Working with Azure IoT Edge might be difficult sometimes seeing some of the errors that are not that easy to understand. That's why I want to provide this dedicated post with Troubleshooting tips in case you get problems.