
Hi !
It’s been a while since I shared some code samples, so here we go today with a simple series based on MediaPipe. MediaPipe is a great Machine Learning platform with cross-platform and customizable ML solutions. And with Python support!
MediaPipe offers customizable Python solutions as a prebuilt Python package on PyPI, which can be installed simply with pip install mediapipe. It also provides tools for users to build their own solutions. Please see MediaPipe in Python for more info.
MediaPipe in Python
MediaPipe have a HandKeypoints Detector, which includes a Python implementation. The full sample runs as this one

It’s cool, and the trained model returns 2D coordinated for the following points:

From here on, to start the test, 1st I needed to install the mediapipe python dependency:
pip install mediapipe
And I cloned this repo and run the app.py sample to get the output from the previous image.
python app.py
A lot of knows friends in the main app including camera processing with OpenCV. In next post, I’ll start to dissect and create a custom apps using this.
Happy coding!
Greetings
El Bruno
More posts in my blog ElBruno.com.
More info in https://beacons.ai/elbruno
References
¿Con ganas de ponerte al día?
En Lemoncode te ofrecemos formación online impartida por profesionales que se baten el cobre en consultoría:
- Si tienes ganas de ponerte al día con Front End (ES6, Typescript, React, Angular, Vuejs…) te recomendamos nuestros Máster Front End: https://lemoncode.net/master-frontend#inicio-banner
- Si te quieres poner al día en Backend (stacks .net y nodejs), te aconsejamos nuestro Bootcamp Backend: https://lemoncode.net/bootcamp-backend#bootcamp-backend/banner
- Y si tienes ganas de meterte con Docker, Kubernetes, CI/CD…, tenemos nuestro Bootcamp Devops: https://lemoncode.net/bootcamp-devops#bootcamp-devops/inicio