Last week, the Coral team released updates to the Coral platform to "address customer feedback and make it easier to use the products and tool-chain". The Python API has now the ability to run multiple models in parallel, using multiple Edge TPUs.

Thus, due to the multiple changes, I updated the Docker image lemariva/raspbian-edgetpu which includes the Edge-TPU libraries for Raspberry Pi 3 B+, Jupyter Notebooks and some other interesting libraries (check the Dockerfile).

Fig 1: Coral USB Accelerator, Jupyter and some training objects

The base Docker image remained balenalib/ras...

Last week, I published an article about using Xiaomi sensors without a Xiaomi Gateway. The gateway/hub can be replaced with a Raspberry Pi and a USB-ZigBee dongle. You find the instructions here: #ZigBee: Xiaomi Sensors using Raspberry Pi (without Gateway!).

As you can read in that article, two repositories are available to connect and process the data from the Xiaomi sensors. Additionally, Zigbee2mqtt can be connected to Hass.io. Well, I didn't want to use HassOS (the OS on which hass.io runs), but I wanted to use Hass.io running on Raspbian, otherwise with Home Assistant running as an appli...

This week, I received from Seeed Studio a MAiX Dock to review it. The main board of the kit includes a Sipeed M1w which is a compact module like the ESP32 but based on the Kendryte K210 dual core RISC-V processor. It is designed for low power artificial intelligence workloads, such as face detection, object recognition, or audio processing. There are two type of modules: the Sipeed M1 and M1w, the last one includes WIFI connectivity.

The main features of the MAiX Dock boards are:

1. Display I/F – An FPC24P socket for 8-bit MCU LCD
2. Camera I/F- An FPC24P socket for DVP camera
3. Storage – micro SD s...

This post is about data inside Docker containers. As I mentioned in the last post #Analytics: Docker for Data Science Environment, data in Docker can either be temporary or persistent. In this tutorial, I will focus on Docker volumes, but I will include some info about temporary data and bind mounts too.

Fig 1: Data in Docker container (source)

Temporary Data

Inside a Docker container, there are two ways in which data can be kept temporarily. By default, files created inside a container are stored in the writable layer of the container. You do not have to do anything, but every...

This tutorial allows you to connect Xiaomi (or Aqara) sensors (e.g. door, pir, temperature, water, switch) to a Raspberry Pi or similar system without using any Xiaomi Gateway.

This is what I will try to accomplish in this tutorial:

1. Flash the USB-Zigbee Dongle with the correct FW
2. Install a broker to connect to the sensors
3. Configure the sensors using the broker

Hardware

Xiaomi sensors use Zigbee for the connection which means we need some extra components to connect to them. This is the list of needed hardware:

This is just another small post. I was quite busy the last weeks, and here is why:

Next week (from April 1st to April 5th), I'll be at the Hanover Fair 2019.

I am with our start-up fine|alyze presenting solutions for IIoT and data analytics. If you want to meet me in person, just come to the Hall 16, Stand D38(1) -5G Arena-.

We are collecting and analyzing the data produced by a "model factory" of VWN, and presenting live results of our models.

Click here to find the map!

In summer 2018, Google announced two Edge TPU devices for machine learning. These are now available under the Coral brand. Two weeks ago, I bought the Coral USB Accelerator. It is a portable USB accessory that brings machine learning inferencing to existing systems and it is compatible with Raspberry Pi and other Linux systems.

Fig. 1: Coral USB Accelerator, Raspberry Pi Camera and a RasPad

I wanted to test the performance of the Edge-TPU on my Raspberry Pi3, and as I have every application running on Docker on my Raspberry Pi, I've created a Docker image with everything inside t...

Just a small post. I've migrated the blog from Pagekit CMS to OctoberCMS. Pagekit was a nice CMS, but unfortunately the project is almost dead, so I've decided to migrate to OctoberCMS.

Why I didn't choose Wordpress? Well, I hate Wordpress. I've tried a lot, but everytime I found that it was not for me.

So, I have a ToDo for you: If you find something that it is not working, please use the contact formular or the comment section below to inform me! I've checked everything, but I've migrated almost 100 pages (articles, static pages etc.) and all the meta information and probably I forgot some...

This month, I received the M5Stack FIRE development kit with a PLC base kit from Banggood to review (see Fig. 1). After using it, I can affirm that the M5Stack takes an alternative approach to ESP32 prototyping, because the resulting projects are almost simultaneously finished products. This is possible because the board is housed in a stylish and robust hosing with graphics display, buttons, microSD card slot, USB-C port and speakers. I tested the M5Stack FIRE development kit, and the board includes also a MPU6050, MAG63110 (MPU9250 on the new versions), BSE3729 and a PSRAM to extend the ESP3...

A good friend of mine has an old printer and he was always thinking of buying some adapter to make it Wi-Fi compatible. He actually bought one, but it was not compatible! I told him to buy a Raspberry Pi W Zero and build a CUPS Print Server, but he did not have time to do that, so I planned as XMas gift! I hope he is not going to read this before he gets his present. :) - If you received this as a gift, your instructions are here.

A big challenge was to make it plug & play. I did not want to have his Wi-Fi credentials, and he should not use a terminal over SSH to configure it. I looked for som...

This time a quick tutorial to control your WiPy 3.0 / 2.0 or an ESP32 using Blynk.

Blynk is the most popular mobile app for the IOT. Works with anything: ESP8266, Arduino, Raspberry Pi, SparkFun and others.

I found a library to connect MicroPython to Blynk but it is only compatible with the WiPy 1.0. Thus, I modified it and made it compatible with the WiPy 3.0 / 2.0 and with the ESP32 running MicroPython. If you do not have any idea about MicroPython, I recommend you to read this tutorial.

This is what I will try to accomplish in this tutorial:

1. Install MicroPython (if you are using an ESP3...

I was looking at my last articles about MicroPython and my new articles about Jupyter and Docker, and I thought if it is possible to make a mix between Jupyter and the ESP boards. I use usually Visual Studio Code to program the ESP but for analytics I use Jupyter. I looked if it was possible to connect the Jupyter kernel to the ESP using the serial port and: Yes!, it is possible. This can be a great tool to teach kids to access data from connected sensors and analyze it using a browser with Jupyter.

This is what I will try to accomplish in this tutorial:

1. Install MicroPython
2. Install the Jupyte...

Out with the old, in with the new! Happy 2019!

It's been a two years now since I started this blog. It's a hard job to maintain it up-to-date but I still have fun writing and coding for this purpose! I hope the next year will be better than this one! :)

This post includes a new video for happy new year! The video combines some of the MicroPython code, that I've published this year. I'll be uploading the repo to GitHub in the next days. But, in the meantime enjoy the video, and check the MicroPython projects here!

Portainer is a management UI which allows you to easily manage your different Docker environments.

This is what I will try to accomplish in this tutorial. You will be able to:

• Run Portainer for Docker management on Windows, Linux and on a Cloud platform
• Start container with a predefined admin password, in case you are on a public network

Linux/Mac OSX

If you are running Docker on Ubuntu or Mac OSX, you can start using Portainer as a Docker Container typing the following:

docker volume create portainer_data
docker run -d -p 9000:9000 --name portainer --restart always -v /var/run/docker.sock:...

Quoting the official MicroPython's website:

MicroPython is a lean and efficient implementation of the Python 3 programming language that includes a small subset of the Python standard library and is optimised to run on microcontrollers and in constrained environments.

Besides C++ and C, I use MicroPython to program microcontrollers, especially the ESP32/ESP8266 types. These two microcontrollers are compatible with MicroPython and it is easy to integrate sensors and actors programming using this language. I wrote a tutorial about installing MicroPython on the ESPs, as well a lot of articles a...