TensorFlow

The project focuses on developing a predictive tool for chess using recurrent neural network (RNN) models implemented in TensorFlow. Data collection was carried out using web scraping techniques from the website https://www.chess-poster.com.

El proyecto se orienta hacia el desarrollo de una herramienta predictiva para el ajedrez, empleando modelos de red neuronal recurrente (RNN) implementados en TensorFlow. La recopilación de datos se realizó mediante técnicas de web scraping desde la página https://www.chess-poster.com.

This project provides a deep learning approach to learn machining features from CAD models using a hierarchical graph convolutional neural network.

Transform text into lifelike speech with advanced neural network models

Exact and differentiable spherical harmonic and Wigner transforms for TensorFlow

Splits the Audio into multiple streams (vocal, drums, guitar etc.) based on the Deep Learning.

Docker images with different flavors for research (Tensorflow and Pytorch)

Project containing manifests for deploying tfserving on kubernetes. The goal is to have parameterized deployments that pull from external models (or models not built directly into the container, even attached as Volume works)

A simple Python GPT2 API

Playground to get started with training NN on azure cloud

docker nuxt flask

Haruspex is a Convolutional Neural Network capable of recognizing and predicting secondary structure elements and nucleotides in Cryo-EM reconstruction density.