Project for the course DeepLearning. Written in PyTorch, trained and evaluated on the Market-1501 dataset.
Project for the course Natural Language Understanding. The goal of this project was to test 2 BERT-based italian models on multiple italian datasets from different domain, in order to compare their performances and to assess their generalization capabilities, with and without finetuning.
Project for the course Signal,Image, and Video. The goal was to extend classical rigid-trackers to allow the tracking of deformable shapes.
This is my thesis about "Unsupervised learning for customer segmentation and its interpratability"
This is the presentation of our work during SoccerDataChallenge19 in Trento (feat. Matteo, Francesco and Jacopo)