Oscar A. Rangel's Projects
Udacity ND for Path/Route Planning on OpenStreetMap using A* Search Algorithm. It uses IO2D library for the graphics rendring.
Adaptive Learning Rate
APTOS 2019 Blindness Detection Detect diabetic retinopathy to stop blindness before it's too late
DeepRacer workshop content
This C++ project is the fifth and final project of the Udacity C++ Nanodegree
LlamaIndex is a simple, flexible interface between your external data and LLMs
This project demonstrates a robust Continuous Deployment (CD) pipeline designed to streamline the process of deploying applications. Leveraging industry-standard tools and practices, this repository provides a comprehensive setup for automating the deployment of code changes to production environments efficiently and reliably.
This is the project for the fourth course in the [Udacity C++ Nanodegree Program](https://www.udacity.com/course/c-plus-plus-nanodegree--nd213): Concurrency.
GPT-4o can interact with the API using voice commands, and the API will be able to understand and respond to those commands.
Purpose : In this project you will analyze and modify an existing ChatBot program, which is able to discuss some memory management topics based on the content of a knowledge base. The program can be executed and works as intended. However, no advanced concepts as discussed in this course have been used. There are no smart pointers, no move semantics and not much thought has been given on ownership and on memory allocation.
El modelo keras se crea al entrenar SmallerVGGNet desde cero en alrededor de 2200 imágenes faciales (~ 1100 para cada clase). La región de la cara se recorta aplicando face detectionusando cvliblas imágenes recopiladas de Google Images. Obtuvo alrededor del 96% de precisión de entrenamiento y ~ 90% de precisión de validación. (20% del conjunto de datos se usa para la validación)
Unlike Eigenface and Fisherfaces we use CNN/OpenFace Enrollment
Face Identification software developed in C#
Temporary home for fastai v2 while it's being developed
La libreria de alto nivel para aprender e implementar Redes Neunorales con Pytorch
Challenges in Representation Learning: Facial Expression Recognition Challenge
Filters 4 Face Recognition
This is a repo for building out Github Actions and Tricks. I test multiple clouds and multiple versions of Python.
This is a project to auto-deploy with an ML payload
Example Github Actions Project designed to show how to connect to all three mayor shell
Guanaco Spanish finetuned LLaMA Model like ChatGPT
Identify glomeruli in human kidney tissue images
Iris recognition systems are being used in access control applications. Several airports are using biometric systems including iris recognition steps for granting access to frequent fliers and decreasing the waiting time at security checkpoints.
This project is based on PCL library that is used to read and process point cloud data obtained using 3D Lidar sensor. Aim is to detect 3d obstacles (other vehicles) in the surrounding of the ego vehicle and create appropriate bounding boxes around them. This repository has code for both the custom (implemented by me) as well as PCL's built in segmentation and clustering methods.
Execute a quick model similar to ChatGPT on your personal device. The video demonstration shown below is not accelerated and is being performed on an M1 Mac studio utilizing 4GB of weight.
A detailed Tutorial showing the process of fine-tuning a causal language model using LoRA (Low-Rank Adaptation).
Performance with MNIST dataset
Models and examples built with TensorFlow