Filed under
4 blog posts and projects filed under this tag, newest first.
Entries
4
For my bachelor thesis, I built ISeeUNet, a modified U-Net trained on hybrid real and synthetic datasets for real-time change detection on Nvidia Jetson NX hardware.
My second homelab replaced a Raspberry Pi with a loud, power-hungry Dell R710. It taught me where capacity helped, where it hurt, and what the failures changed.
Read dispatchI built a Python and scikit-learn product classifier for 5,000+ COICOP categories at a three-day ECB hackathon. Word embeddings and logistic regression reached 99.82% accuracy.
I led a university team building autonomous navigation for a TurtleBot, benchmarking control algorithms and shipping a ROS/Python system that handled an unknown obstacle course.