pptr3
Focus on Computer vision and Deep learning. MSc in Artificial Intelligence and BSc in Computer Science and Engineering.
Pinned Repositories
connecting-rods
Computer vision system aimed at visual inspection of motorcycle connecting rods.
face-generation-gan-keras
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 generation of conditioned faces and a score of 11.07 for the gen- eration of random faces.
image-captioning-keras
Image captioning using Bahdanau and Luong attention applied on COCO and Flickr8k datasets. The performances have been measured using BLEU and METEOR scores.
machine-learning-ng
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
math-assistant
Mobile (iOS) application for analysis and recognition of handwritten mathematical operations. The goal is to understand if the operation is correct or not. If it is not, it shows you the correct result.
ML4CV
pancake-fp
E-commerce website for booking pancakes .
pptr3
My personal repo.
road-sings-recognition-pytorch
Multiclass classification model for the recognition of 21 different road signs used in autonomous car systems using pytorch.
super-smarket
Decision support software which analyzes market's products and suggests you when is the right moment to put them in discount in order to maximize the market gain.
pptr3's Repositories
pptr3/ML4CV
pptr3/pancake-fp
E-commerce website for booking pancakes .
pptr3/pptr3
My personal repo.
pptr3/analysis-data-exploration
My notebooks of Analysis Data Exploration course -> https://www.youtube.com/watch?v=rqFkYfldG_Q
pptr3/face-generation-gan-keras
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 generation of conditioned faces and a score of 11.07 for the gen- eration of random faces.
pptr3/nlp-assignments
pptr3/personal-blog
My personal blog: https://potrimba.altervista.org
pptr3/polygons-vs-bbox
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.
pptr3/TablutAI
AI that plays Tablut better than you.
pptr3/temperature-anomaly-detection
This notebook contains several anomaly detection techniques useful to find anomalies on a time series signal.
pptr3/connecting-rods
Computer vision system aimed at visual inspection of motorcycle connecting rods.
pptr3/image-captioning-keras
Image captioning using Bahdanau and Luong attention applied on COCO and Flickr8k datasets. The performances have been measured using BLEU and METEOR scores.
pptr3/machine-learning-ng
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
pptr3/road-sings-recognition-pytorch
Multiclass classification model for the recognition of 21 different road signs used in autonomous car systems using pytorch.
pptr3/backpropagation-nn
Classic implementation of the backpropagation algorithm for training a Neural Network with only one hidden layer.
pptr3/bayesian-network-mma
pptr3/cqs
pptr3/dotnet_course
pptr3/enriched-content-nlp
pptr3/extreme_3d_faces
Extreme 3D Face Reconstruction: Looking Past Occlusions
pptr3/fruit-inspection
Computer vision techniques applied to apple images to detect apple's defects.
pptr3/GlobaLeaks
GlobaLeaks is free, open source software enabling anyone to easily set up and maintain a secure whistleblowing platform.
pptr3/icevision
An Agnostic Computer Vision Framework - Pluggable to any Training Library: Fastai, Pytorch-Lightning with more to come
pptr3/kpi6-test
pptr3/maskRCNN_educative
pptr3/master
pptr3/present-wrapping-csp-smt
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.
pptr3/send-time-optimization
pptr3/t81_558_deep_learning
Washington University (in St. Louis) Course T81-558: Applications of Deep Neural Networks
pptr3/xml-to-json-annotations
Convert annotations from XML (Pascal VOC style) to JSON (COCO style) for Object Detection.