Cloud-Native Edge Computing Signals a New Era of Digital Transformation

Edge Computing places workloads closer to where data is created and where actions need to be taken and address the unprecedented scale and complexity of data created by connected devices. As more and more data come from remote IoT edge devices and servers, it’s important to act on the data that makes the biggest impact. Acting quickly on the right ...
Read More

Cloud-Native Solution: Build a Server Cluster with Docker Swarm

Containers have become popular thanks to their focus on consistency across platforms from development to production. The rise in interest to containers has in turn brought in higher demands for their deployment and management. Docker provides a simple solution that is fast to get started with while Kubernetes aims to support higher demands with higher complexity. For many of the ...
Read More

Cross-architecture Kubernetes with Edge Devices Using Hybrid Cloud Strategy

Kubernetes has rapidly become a key ingredient in edge computing. With Kubernetes, companies can run containers at the edge in a way that maximizes resources, makes testing easier, and allows DevOps teams to move faster and more effectively as these organizations consume and analyze more data in the field. Now, containers are transforming the way edge and IoT platforms have ...
Read More

Cloud Computing Series #2 — Setting Up Your Computing Engine for CUDA AI Development with GCP

Cloud computing is the delivery of on-demand computing services -- from applications to storage and processing power -- typically over the internet and on a pay-as-you-go basis. In the Cloud Computing Series posts, we will walk through the following topics: Setup a Compute Engine on GCPSetup a proper environment for AI developmentDeploy AI applications on the Cloud In this post, ...
Read More
/ / Cloud, Cloud Computing

Face Recognition API on the Jetson

When it comes to Face Recognition there are many options to choose from. While most of them are cloud-based, I decided to build a hardware-based face recognition system that does not need an internet connection which makes it particularly attractive for robotics, embedded systems, and automotive applications. The project is built based on Dlib that is able to compile with ...
Read More
/ / Edge AI, IoT, Jetson

TensorRT Object Detection (DetectNet + OpenCV)

Recently, I found a very useful library that can utilize TensorRT to massively accelerate DNN (Deep Neural Network) application -- the Jetson-Inference Library developed by Nvidia. The Jetson-Inference repo uses NVIDIA TensorRT for efficiently deploying neural networks onto the embedded Jetson platform, improving performance and power efficiency using graph optimizations, kernel fusion, and FP16/INT8 precision. Vision primitives, such as imageNet ...
Read More
Loading...