Poeticoding

Nerves powered Vision - Deploy YOLOv8 on RPi5 with Hailo8L

Fri, 05 Sep 2025 10:53:08 +0000

YOLO for Elixir: https://github.com/poeticoding/yolo_elixir
NxHailo repo: https://github.com/vittoriabitton/nx_hailo
Hailo model zoo: https://github.com/hailo-ai/hailo_model_zoo/
nerves_system_rpi5: https://github.com/nerves-project/nerves_system_rpi5

Most of the code used in the video: https://github.com/vittoriabitton/nx_hailo/blob/main/nx_hailo/livebooks/remote_device_inference.livemd

Building a YOLOX Plate Detector - Setup, Fine-Tuning, Metrics, Dashcam inference

Fri, 29 Aug 2025 17:04:59 +0000

Notes and Code

Install YOLOX and needed deps

Download YOLOX GitHub repo: https://github.com/Megvii-BaseDetection/YOLOX

Then be sure you are using Python <= 3.11 (I had some issues with python 3.12 and switching to 3.11 made all much easier).

Build a Parking sensor with ESP32 board, LEDs and Ultrasonic distance sensor

Wed, 23 Jul 2025 15:27:53 +0000

What problem am I trying to solve?

My garage was built for cars from another era: inside it’s about ~4.8 m long × 2.5 m wide, and the entrance narrows to just 2.2 m. My car, on the other hand, is 4.7 m long and almost 2 m wide, so squeezing it through the doorway is just step one. Even if I make it in without scraping the sides, I’m stuck: there’s almost no room between the car and the side walls, so I can’t open the door or shut the garage door behind me. I need to use every last millimeter of length, but no matter how gently I press the pedal, or how much I rely on the factory cameras, getting the exact distance to the back wall is nearly impossible.

Fine-Tuning YOLO to Watch Soccer Matches

Thu, 17 Jul 2025 15:14:24 +0000

Today we’re diving into something really cool: fine-tuning YOLO models for soccer detection. We’re going to detect balls, referees, players, and goalkeepers in soccer matches using Ultralytics’ fine-tuning tools.

The popular YOLO models you’ll find out there, like Ultralytics YOLOv11, and YOLOX in different sizes, are mostly pre-trained on something called the COCO dataset.

Elixir YOLO v0.2.0: YOLOX Support, Custom Models and Performance Boost

Thu, 26 Jun 2025 15:59:25 +0000

https://github.com/poeticoding/yolo_elixir/releases/tag/0.2.0

In the four months since my daughter was born, I’ve been balancing baby bottles by night and code commits by day. Finally managed to ship this release, sleep-deprived, but very proud!

This isn’t just a version bump, it’s a major release, introducing three key enhancements:

Effortless Video Sharing with Phoenix LiveView and FLAME

Thu, 28 Nov 2024 18:09:06 +0000

As someone who loves experimenting with new technologies, I recently got the Vision Pro (I’m a big fan of VR and the idea of working in mixed reality). What excites me the most is sharing the cool stuff I discover, with my friends and colleagues, like how amazing it is to have a floating 3D model in mixed reality, built with just a few lines of Swift code.

Phoenix LiveView LiveComponents

Tue, 23 Nov 2021 16:09:36 +0000

Course Index page

Code

Links

We’ve just started to build our CryptoDashboardLive view, and we already have the feeling that the we are piling up a lot of code into the single CryptoDashboardLive module. It’s not just about the template in the render/1 function, we could easily move it into a .leex file. The risk is to find us with a single massive live view module which handles every aspect of our page, making che code hard to read and maintain. This page already has different parts with different responsibilities, for example: product cards where each one shows its product price, a toolbar with a dropdown to add products to the dashboard…

A nice Dashboard UI

Tue, 23 Nov 2021 15:35:40 +0000

Course Index page

Code

Before going on with LiveComponents and other topics, let’s spend a few minutes on our UI. At the moment products and trades are rendered in a table, using the default phoenix.css.

Bindings, Click and Form events, Debounce, Live Flash messages

Wed, 30 Jun 2021 11:24:56 +0000

Course Index page

Code

Links

Until this moment we only dealt with a passive view, which receives updates from the server, but that doesn’t provide any user interaction.

Layouts and LiveEEx templates

Tue, 25 May 2021 11:14:16 +0000

Course Index page

Code

lv-first-view branch

Links

We’ve previously seen in detail how Phoenix LiveView works. In this lesson we are going to see:

How Phoenix LiveView works

Tue, 27 Apr 2021 11:20:08 +0000

Course Index page

Code

How does LiveView work?

In the previous lesson we got a taste of the LiveView’s magic! In this lesson we are going to see how LiveView really works and what happens behind the scenes when a user connects.

First contact with Phoenix LiveView

Tue, 13 Apr 2021 18:46:05 +0000

Course Index page

Code

Our first Live View

In this lesson we’ll introduce LiveView and get a sense of how powerful it can be. In the next lesson we’ll see better how LiveView works under the hood.

Intro to Poeticoins Elixir application

Sat, 27 Mar 2021 11:51:14 +0000

Course Index page

Poeticoins GitHub repository: poeticoding/poeticoins

Application Design

Tue, 23 Mar 2021 18:43:56 +0000

Course Index page

In this course we’ll build a Phoenix LiveView app (called Poeticoins) that gets real-time trades from multiple cryptocurrency exchanges and, with LiveView, it displays prices, and other data, on an interactive dashboard.

Since the dashboard just shows the most recent data, we won’t need any database. We’ll see how to use Elixir processes to temporarily keep all we need in memory.

Intro to Cryptocurrency Exchanges

Tue, 23 Mar 2021 16:22:16 +0000

Course Index page

I’ve decided to build this Phoenix LiveView course around a Cryptocurrency dashboard example because Cryptocurrency Exchanges are a fantastic, often public, source of realtime data. Don’t be scared if you don’t know anything about cryptocurrencies or exchanges, I’m going to explain everything we need to start playing with this data.

Compile Elixir applications into single executable binaries, with Bakeware

Thu, 22 Oct 2020 16:24:50 +0000

Bakeware is a new fantastic tool, built (by Frank Hunleth, Jon Carstens and Connor Rigby) over a weekend for the SpawnFest 2020, which compiles an Elixir, a Scenic or a Phoenix application into single executable binary (yes, like go-lang!). It can be extremely useful to distribute our apps, especially when they are command-line tools or Scenic applications.

Yet Another Guide To Build a JSON API with Phoenix 1.5

Tue, 06 Oct 2020 20:36:16 +0000

We are going to build a polling app step-by-step. It will be similar to strawpoll.me where users can create and vote on polls and see the results in real-time.

In this blogpost we will only create the basic version of this app and in later blog posts we will add more features like authentication, ip blocking, different voting types and more.

LiveView click event and offsetX, offsetY coordinates

Thu, 19 Mar 2020 17:05:47 +0000

Phoenix LiveView plays fantastically well with SVG elements, making really easy to render dynamic images, without writing any JavaScript code.

There are different bindings we can use to register and react to user interaction, one of these is phx-click. By adding phx-click="clicked" attribute to an element in our LiveView, when user clicks the element, a "clicked" event is sent to the LiveView process.

Phoenix LiveView JavaScript Hooks and Select2

Wed, 05 Feb 2020 11:48:10 +0000

We’ve already played with Select2 and LiveView, it was before the release of LiveView JS Hooks. To make select2 work with LiveView we had to listen to phx:update generic javascript events, re-initialize select2 and use a workaround to push events from the browser to LiveView.

Real-time Object Detection with Phoenix and Python

Thu, 16 Jan 2020 18:43:14 +0000

This article is not just about Machine Learning and Object Detection, it’s about Elixir interoperability and how we can take advantage of the Python’s fantastic set of ML libraries, bringing their features into the Elixir world.

We see how to bring YOLO, a state-of-the-art real-time object detection system, in a Phoenix web app.