This repo contains the python codes of my final thesis "Analysis of leaf species and detection of diseases using image processing and machine learning methods".

This project implements a deep learning–based image classification system to accurately distinguish between cats and dogs Using transfer learning with a pre-trained ResNet50 model

COVID-19-Xray-Dataset Deep Learning using 3 models

Classifying MonkeyPox Images using various Deep Learning networks (VGG16,VGG19,RESNET50 and a Custom CNN model)

Project for the University Master Degree Course of Statistical Methods for Machine Learning.

A supermarket chain called Good Seed wanted to see if Data Science could help them comply with the law by ensuring that they did not sell age-restricted products to underage customers. My task was to build and evaluate a model to verify a person's age.

Successfully established an image classification model using PyTorch to classify the images of several distinct natural sceneries such as mountains, glaciers, forests, seas, streets and buildings with an accuracy of 86%.

Odelia Breast MRI Challenge

Classifying Pneumonia images and normal lung images using RESNET50 and Customized CNN models.

Bias-aware multimodal pancreatic cancer detection using CT imaging and urinary biomarkers, with ResNet50 CT modelling, biomarker MLP classification, and exploratory fusion analysis.

A predictive analytics in Fishery using Deep learning techniques. It includes classifying what type of fish it is and also the disease it is affected with.

Brain Tumor MRI classification using ResNet50 feature extraction, end-to-end fine-tuning, and EfficientNet-B0.

Goal : Create 20 image clusters using different clustering algorithms and various features.

Cette application utilise l'apprentissage automatique pour reconnaître et classifier les espèces de fleurs à partir d'images, fournissant des informations détaillées pour faciliter l'identification des plantes.

This repository implements the full training pipeline for the DermAI skin lesion classifier using 3-fold stratified cross-validation and ResNet50 fine-tuning.