JoaoLages

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

simpletransformers

Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI

autogluon

Fast and Accurate ML in 3 Lines of Code

cugraph

cuGraph - RAPIDS Graph Analytics Library

pytorch-styleguide

An unofficial styleguide and best practices summary for PyTorch

PCGrad

Code for "Gradient Surgery for Multi-Task Learning"

higher

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

anchor

Code for "High-Precision Model-Agnostic Explanations" paper

captum

Model interpretability and understanding for PyTorch

tf-explain

Interpretability Methods for tf.keras models with Tensorflow 2.x

checklist

Beyond Accuracy: Behavioral Testing of NLP models with CheckList

statsmodels

Statsmodels: statistical modeling and econometrics in Python

restler-fuzzer

RESTler is the first stateful REST API fuzzing tool for automatically testing cloud services through their REST APIs and finding security and reliability bugs in these services.

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

tslearn

The machine learning toolkit for time series analysis in Python

IR-query-clustering

Adabelief-Optimizer

Repository for NeurIPS 2020 Spotlight "AdaBelief Optimizer: Adapting stepsizes by the belief in observed gradients"

einops

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

DeepTables

DeepTables: Deep-learning Toolkit for Tabular data

graphbrain

Language, Knowledge, Cognition

great_expectations

Always know what to expect from your data.

first-order-model

This repository contains the source code for the paper First Order Motion Model for Image Animation

ydata-profiling

1 Line of code data quality profiling & exploratory data analysis for Pandas and Spark DataFrames.

TrustScore

To Trust Or Not To Trust A Classifier. A measure of uncertainty for any trained (possibly black-box) classifier which is more effective than the classifier's own implied confidence (e.g. softmax probability for a neural network).

faiss

A library for efficient similarity search and clustering of dense vectors.

dtale

Visualizer for pandas data structures

optuna

A hyperparameter optimization framework

uda

Unsupervised Data Augmentation (UDA)

gin-config

Gin provides a lightweight configuration framework for Python

featuretools

An open source python library for automated feature engineering