Nícolas Pauli's repositories
Build-an-ML-Pipeline-for-Short-Term-Rental-Prices-in-NYC
Starter Code for the Course 2 project of the Udacity ML DevOps Nanodegree Program
Computer-pointer-controler
This project is a computer vision application developed with Intel Distribution of OpenVINO. This application was developed to control the computer pointer controler through the gaze estimation of the eyes. This program can be feed with a video file or a webcam. It was used four models to run Face Detection, Facial Landmarks Detection, Head Pose Estimation and Gaze Estimation all provided by OpenVINO.
CVND_Exercises
Exercise notebooks for CVND.
Deploy-a-People-Counter-App-at-the-Edge
Developed an application that allows count people in a screen.
Deploying-a-sentiment-analysis-model
This project is a deployed sentiment analysis model using AWS SageMaker.
Dog-Breed-Classifier
This project accepts any user-supplied image as input. If a dog is detected in the image, it will provide an estimate of the dog's breed. If a human is detected, it will provide an estimate of the dog breed that is most resembling.
DSND_Term1
Contains files related to content and project of DSND
DSND_Term2
Contains files related to content and project of DSND Term 2
Face-Generation
Created a DCGAN model on a dataset of faces. The goal was to get a generator network to generate new images of faces that look as realistic as possible!
Operationalizing-Machine-Learning
Created a Machine Learning project using Azure to configure a cloud-based machine learning production model, deploy it, and consume it.
Optimizing-an-ML-pipeline-in-Azure
Created and optimized an ML pipeline using Azure. Built a custom-coded model, a standard Scikit-learn Logistic Regression, tuning the hyperparameters using HyperDrive. Created an AutoML to build and optimize a model on the same dataset and compared the results of the two methods.
Predicting-biking-sharing-patterns
This project created a neural network and use it to predict daily bike rental ridership
Smart-Queuing-System
Given real-world scenarios to build a queuing system, this application identify which hardware types work best, and then test the application using the Intel DevCloud.
TV-scripts-generator
In this project, it is generated Seinfeld TV scripts using RNNs. It was used part of the Seinfeld dataset of scripts from 9 seasons. The Neural Network built generates a new ,"fake" TV script, based on patterns it recognizes in this training data.