Have you ever looked up at the night sky and wondered: How fast are those galaxies moving? The universe is constantly expanding, and galaxies are racing through space at unimaginable speeds. Astronomers use a technique called redshift and blueshift to measure whether galaxies are moving toward ...

Read more ...

The Raspberry Pi Pico never ceases to amaze! I love pushing CircuitPython to its limits. In this article, we dive into using CircuitPython, Fast Fourier Transform (FFT), and a budget-friendly microphone breakout board to recognize flute notes and write them on an OLED screen. Video of the projec ...

Read more ...

When working with Kendryte K210 boards, a cost-effective option for edge AI projects, you’ll quickly notice that the documentation is often limited. After spending significant time researching and experimenting, I decided to document my process to help others save time when building a Convolutional ...

Read more ...

For some time, I’ve been deeply engrossed in the challenge of training a custom model for my Maix Dock M1, a K210 board. This journey hasn’t been without its frustrations, especially due to the lack of comprehensive documentation, which turned out to be a significant hurdle. However, after a lo ...

Read more ...

I recently bought a Maix Dock M1, which is a neat little device with a K210 neural network accelerator. The kit also included a small LCD display, which I was excited to try out. However, there was one problem—there was no case for the mainboard and the LCD. Handling the camera and the LCD togethe ...

Read more ...

When I engage with students and aspiring job seekers, a common question arises: “What roles can I pursue in the software industry?” or “What skills are needed to become ‘X’ in a software company?” To address these queries, I have developed a user-friendly application. By visiting this url, you can ...

Read more ...

Today we explore the impressive performance of Kendryte K210 and MicroPython in image segmentation and recognition tasks. The K210 delivers impressive speeds, hitting around 10 fps (without a attached display) and 2-3 fps with a display on the MNIST digit recognition task, running from a smaller tha ...

Read more ...

Previously, I implemented handwritten digit classification using CircuitPython and an SVC classifier. While this approach was innovative, it had its limitations, including low accuracy and an inability to handle larger images. Recently, I experienced limited success porting some deep neural networks ...

Read more ...

When considering tooling for TinyML on microcontrollers, you might initially think that CircuitPython isn’t the best tool for the job. After all, it is interpreted and significantly slower than compiling something written in C++ using TFLite micro. While I acknowledge the capabilities of TFLite mic ...

Read more ...

Imagine packing the intelligence of a neural network into a device smaller than your palm - how tiny can we go? It turns out, pretty small! With the right techniques, we can run some serious AI on a modest board like the Raspberry Pi Pico. In this article I discuss how we can create a single word s ...

Read more ...