The fastai deep learning library

A game theoretic approach to explain the output of any machine learning model.

A small package to create visualizations of PyTorch execution graphs

A python library for decision tree visualization and model interpretation.

Repository containing notebooks of my posts on Medium

A collection of 85 minority oversampling techniques (SMOTE) for imbalanced learning with multi-class oversampling and model selection features

Original transformer paper: Implementation of Vaswani, Ashish, et al. "Attention is all you need." Advances in neural information processing systems. 2017.

Audio transforms for FastAI

Pytorch notebook with One Cycle Policy implementation (https://arxiv.org/abs/1803.09820)

PyTorch implementation of "MIDA: Multiple Imputation using Denoising Autoencoders"

Official Julia Docker image + Miniconda3 + JupyterLab from conda-forge

MobileNetV2 for fastaiV1 (pretrained and with [optional] batchnorm fusion)