marcospiau

rerankers

awk-hack-the-planet

Source code repo for Ben Porter (FreedomBen)'s talk at Linux Fest Northwest 2019 and 2020

BankMarketingDataSet

bm25-cisi

ir-utils

Gaggle of information retrieval codes I found myself re-writing constantly

t5-deep-ocr-extractor

Scanned receipts information extraction with Google Vision and T5 models

boruta_py

Python implementations of the Boruta all-relevant feature selection method.

ColBERT-pt

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22)

curso_audio

Curso introdutório (e interativo) de análise e síntese de áudio usando iPython Notebook e sklearn.

datasets

TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...

dotfiles

Dynamic-Risk-Assessment-System

The fourth project in the Machine Learning DevOps Nanodegree by Udacity.

EE641_lab_eletronica2

Laboratório de eletrônica 2 - 2s2016 - Turma P

gpt-neo

An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.

ia368-dd-dl4ir

mesh

Mesh TensorFlow: Model Parallelism Made Easier

ml-devops-eng-nanodegree-churn-prediction

ml-devops-nanodegree-project-course-4

Final project for fourth course of Udacity's MLOPS Nanodegree "4. Deploying a Scalable ML Pipeline in Production"

nd0821-c2-build-model-workflow-exercises

Exercise Code for Course 2 of the Udacity ML DevOps Nanodegree Program

nd0821-c2-build-model-workflow-starter

Starter Code for the Course 2 project of the Udacity ML DevOps Nanodegree Program

PTT5

Repository for training T5 to portuguese.

pytrends

Pseudo API for Google Trends

titanic-kaggle

Estudos usando a competição "Titanic: Machine Learning from Disaster" do Kaggle