SKAI is a machine learning based tool for performing automatic building damage assessments on aerial imagery of disaster sites.

Google Research

This repository contains implementations and illustrative code to accompany DeepMind publications

Implementation of Parti, Google's pure attention-based text-to-image neural network, in Pytorch

Pytorch implementation of stochastically quantized variational autoencoder (SQ-VAE)

Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)

CLU lets you write beautiful training loops in JAX.

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

🧮 A collection of resources to learn mathematics for machine learning

SciPy library main repository

Flax is a neural network library for JAX that is designed for flexibility.

A PyTorch Graph Neural Network Library

ImageNet-Sketch data set for evaluating model's ability in learning (out-of-domain) semantics at ImageNet scale

PyTorch Implementation of OpenAI's Image GPT

Convolutional Network Tutorials (AMMI 2021)

🐥A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI

fastNLP: A Modularized and Extensible NLP Framework. Currently still in incubation.

A Collection of Research Papers by Data Science Nigeria

Code for "Uncertainty Estimation Using a Single Deep Deterministic Neural Network"

Graph-based Attention Model

Simple RNN (Gated Recurrent Units) for predicting a diagnosis

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

NYU Deep Learning Spring 2020