This project uses PyTorch to classify bone fractures. As well as fine-tuning some famous CNN architectures (like VGG 19, MobileNetV3, RegNet,...), we designed our own architecture. Additionally, we used Transformer architectures (such as Vision Transformer and Swin Transformer). This dataset is Bone Fracture Multi-Region X-ray, available on Kaggle.

Photo and Video culling tool using ML vision models in Python

DATA: 606 | Capstone Project

This project collects data from the rvf10k dataset containing 10,000 real and fake pictures of human faces. The program employs a custom CNN architecture to classify images with 85% accuracy.

Transferencia de estilo con CNN y Spectral Modelling Synthesis (SMS)

This code trains a CNN in Keras to classify cell images (infected/uninfected). It sets up data generators, defines model architecture with convolutional layers, applies regularization, configures callbacks, and trains the model for binary classification.

Framework for the automatic creation of CNN architectures

Image Classification using Convolutional Neural Networks: A Deep Learning Approach for Diagnosing Eye Diseases

Project I carried out during my Machine Learning course in the Master.

NN and CNN implementation from scratch in PyTorch with data loading, training, and evaluation phase on CIFAR 100 image dataset

Deliverables relating to the Speech Technology University Unit (Notes Courtesy to Dr. Andrea De Marco)

Fruit Classification using CNN

Calculation of the dimensional progression in Convolutional Neural Networks

Implement VGG19 based NN to design Artistic-Style-Transfer Neural Net using the concept of Generative Adversial Neural Network.

Joint scene classification and semantic segmentation with FuseNet

Study of aircraft engine wear for Safran. (2021)

Implementation of a deep learning model based on the VGG16 neural network to track faces in a video or with a camera in real time.