Here I experimented whether is better to directly train an object detection model on bounding boxes or train it on polygons and then convert the prediction to bounding boxes.

My personal repo.

Convert annotations from XML (Pascal VOC style) to JSON (COCO style) for Object Detection.

Computer vision system aimed at visual inspection of motorcycle connecting rods.

Auxiliary classifier generative adversarial network (AC-GAN) model that can generate synthetic faces conditioned with a specific set of attributes. The FID metric reached a score of 19.42 for the g…

Multiclass classification model for the recognition of 21 different road signs used in autonomous car systems using pytorch.

Image captioning using Bahdanau and Luong attention applied on COCO and Flickr8k datasets. The performances have been measured using BLEU and METEOR scores.

E-commerce website for booking pancakes .

Given a wrapping paper roll of a certain dimension and a list of presents, decide how to cut off pieces of paper so that all the presents can be wrapped.

My personal blog: https://potrimba.altervista.org

This notebook contains several anomaly detection techniques useful to find anomalies on a time series signal.

Computer vision techniques applied to apple images to detect apple's defects.

Classic implementation of the backpropagation algorithm for training a Neural Network with only one hidden layer.

My personal solutions in Octave/MATLAB and Python at the assignments of Machine Learning course on Coursera held by Mr. Andrew Ng. -> https://www.coursera.org/learn/machine-learning

AI that plays Tablut better than you.

My notebooks of Analysis Data Exploration course -> https://www.youtube.com/watch?v=rqFkYfldG_Q