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

MQTT — Wireless Communication Demo

In the previous post, we have covered the basic concepts of MQTT such as Client/Broker, Subscription/Publish, and MQTT's Workflow. In this post, we are going to dig into the MQTT workflow and create a communication channel between devices. Basically, any devices ranging from Desktop, Laptop, to Edge devices can serve as a broker, a client, or both simultaneously. I STRONGLY ...
Read More
/ / IoT, Jetson, MQTT, Raspberry-Pi

Wireless Communication Between Edge Devices Via MQTT Broker/Client

For Internet of Things (IoT) devices, connecting to the Internet is kind of a requirement. Connecting to the Internet allows the devices to work with each other and with backend services. The underlying network protocol of the Internet is TCP/IP. Built on top of the TCP/IP stack, MQTT (Message Queue Telemetry Transport) has become the standard for IoT communications. MQTT ...
Read More
/ / IoT, IoT, MQTT, Softwares

Machine Learning Frameworks — What To Choose?

Machine Learning (ML) is one of the fastest emerging technologies today. ML developers are looking for the right framework for their various kinds of projects for ML application development. Machine learning (ML) is a scientific study of statistical models and algorithms to help a computing system to accomplish designated tasks efficiently and independently by relying solely on inferences and patterns ...
Read More
/ / Machine Learning, Software

OpenCV Quick Start

OpenCV is an open-source computer vision library that has an extensive collection of great algorithms. Since one of the latest mergers, OpenCV contains an easy-to-use interface for implementing Super Resolution (SR) based on deep learning methods. The interface contains pre-trained models that can be used for inference very easily and efficiently. So far, it works with C++ and Python. OpenCV ...
Read More
/ / OpenCV, Python, Softwares

Cloud Computing Series #1 — Train Yolov3 Custom Object Detection Model with Colab

In the previous post, we have walked through the basics of using Google Colab. In this article, we will be doing an experiment on training a custom object detection model on the Cloud ! Let's get started. In this experiment, the custom object detection model will be trained based on a YOLOv3-tiny Darknet Weight. If you have never tried Yolov3 ...
Read More
/ / Cloud, Cloud Computing