PyTorch

A CBIR and classification system that uses both representation learning and handcrafted features to build the image descriptors.

Introduction to classification using machine learning and deep learning (PyTorch, TensorFlow, Keras)

Docker image for develop Ai projects

Este repositorio contiene el código empleado para la resolución del trabajo de fin de grado realizado por Pablo Rubio Carballo para la obtención del título de Grado en ingeniería informática - Ingeniería de computadores. ETSII, Universidad de Sevilla.

расширение исходной модели

Command Line Interface for developers of qary -- the open source, teachable AI assistant that truly assists, rather than manipulating you.

The project entailed building an image classification model using PyTorch, integrated with Azure ML for data handling, model training, and deployment. Key steps included initializing Azure ML Workspace, processing the dataset, developing the model in PyTorch, and deploying it on Azure for real-world inference. This project showcases the synergy between advanced machine learning frameworks and cloud computing platforms in solving complex image classification tasks.

Population density tracker using Computer Vision.

En este trabajo se varían distintos hiperparámetros de una CNN para mejorar la clasificación multiclase de imágenes

Train YOLOv5 for breed classification on Oxford Pets III dataset from scratch on Google Colab, and serve through Dockerized implementation of a flask-based HTML/JS frontend and an asynchronous API service on FastAPI. Use of MLFlow for logging.

Fashion MNIST linear classification model with Keras 3.0 and PyTorch

Vamos a contruir un Chatbot Inteligente capaz de interpretar el lenguaje humano y generar respuestas coherentes con tu propia información

Copy of my kaggle notebooks from account for that time

Simple docker code that trains custom GAN network to generate images (bad quality, but quite fast in docker)

examples of Applied ML

Final project of course ML junior by Skillbox. Goal: Build model to predict client's loan default. Metrics: ROC-AUC