Ignacio Degregori

The Dog App is a single-page application (SPA) that I initially developed as a personal challenge, which eventually became an invaluable learning experience in the field of machine learning and transfer learning. The core functionality of the app revolves around a fine-tuned image classification model that I created. This model utilizes the convolutional layers from MobileNetV3 and incorporates my own custom classifier. It has been trained specifically on images of various dog breeds, enabling… Mostrar más

The Dog App is a single-page application (SPA) that I initially developed as a personal challenge, which eventually became an invaluable learning experience in the field of machine learning and transfer learning. The core functionality of the app revolves around a fine-tuned image classification model that I created. This model utilizes the convolutional layers from MobileNetV3 and incorporates my own custom classifier. It has been trained specifically on images of various dog breeds, enabling it to accurately recognize and classify the breed of a dog from an ed image.
Developed using React JS, the Dog App showcases my proficiency in front-end development. Despite its intentionally minimalistic styling, the app delivers a seamless experience with its intuitive interface. It employs responsive design principles to ensure optimal performance across different devices and screen sizes.
Furthermore, the Dog App leverages TensorFlow JS, a powerful library for machine learning in JavaScript, to execute the image classification on the client-side. This eliminates the need for server-side processing, resulting in faster and more efficient classification results.
To ensure the reliability and accuracy of the app, I implemented unit testing using Jest, a popular JavaScript testing framework. This approach guarantees the functionality of the app's core features and enhances its overall quality. Mostrar menos

This is a small project i built that allows s to search a database of abbreviations in hebrew and see their meaning and decomposition in a graphical manner. It's built entirely in React, Jquery and material-UI.

An online platform that allows teachers to texts so that students can access, create and save summaries of them. It also s the creation of personal links and the creation of anonymous links to allow the correction of summaries without prejudice. It also includes a tool to new texts and for Hebrew text (RLT).

This project allows a teacher to track variables (on a dashboard on his laptop) from sliders of student's phones or laptops in real time. One of this variables is how much the individual student is undestanding the topic, the students can also request the teacher not to move on to the next topic yet. .It also provides data views for further analyzing after the class. It was built using pure React, Material-UI and firebase.

This is a small project for a -less chat service. The chat rooms are cloud stored and end-to-end encrypted. The whole project was made using Firebase, ReactJS, redux, bootstrap and some npm libraries.

this was an experimental project for triangulating the position of a thunder over a city using the time delay reported by multiple s. The project was built on ReactJS, firebase and node. ReactJS with redux was used in the front-end, and the back-end and database and the node code are both hosted on firebase.

https://github.com/idegre/thunderfinder

a very simple library to import, handle and export BMP images in C.

A simple and very lightweight snake game for android, designed for minimalism.