Got a cool project? Share and show off your work.
Feel free to share links to demos, GitHub and posts for your project. You can also submit your project to the TensorFlow Community Spotlight program for the chance to be featured on the TensorFlow Twitter handle.
I worked on various Pre-trained Machine Learning Models on Raspberry Pi. These are computer vision models (Inception and Mobilenets) provided by the Google Coral team.
Though they have provided examples to run these models using sample scripts, I thought it would be a nice idea to make a simple tool using Python & Web dev which can run these 20+ models without having to stop and start the Python script every time you need to test a different model. Further, the tool takes care of Object Detection and Image classification methods dynamically and provides output accordingly.
To simplify the installation process, I have written a bash script using which anyone can configure his/her Raspberry Pi in all respects to run this project. The script automatically installs Tensorflow Lite, OpenCV, all the models and source code of this project on a Raspberry Pi. Basically, a beginner can start seeing the output without having to see the code or worry about it.
I named the tool ‘Model Garden’ and I think it will be useful for students / hobbyists to get started with Machine Learning on a Raspberry Pi or atleast have a feel of these wonderful models without much hassle.
Check this on Github:-
jiteshsaini/model_garden
I created an AI Vision controlled robot that can be controlled from thousands of miles away using TensorFlow + MoveNet (Thunder). Checkout the demo + details here: project proxy.mity. Proxy is a robot designed to make video… | by Saharsh Sinha | Jun, 2024 | Medium