Port of OpenAI's Whisper model in C/C++

Visualize your Google Location History using an interactive heatmap

Cute Chess is a graphical user interface, command-line interface and a library for playing chess.

My notes on how I created my Data Science environment on macOS ARM

Generate Scriptable app widget to query PurpleAir sensor and display local AQI.

The Stockfish chess engine for web browsers

Super Resolution for images using deep learning.

Caffe2 is a lightweight, modular, and scalable deep learning framework.

articles about research and phd advice

Set up a personal VPN in the cloud

List of automatic music tagging research articles that are evaluated against MagnaTagATune Dataset

Turn your two-bit doodles into fine artworks with deep neural networks, generate seamless textures from photos, transfer style from one image to another, perform example-based upscaling, but wait..…

iMessage stickers for your favorite Apple executives

Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit

R-FCN: Object Detection via Region-based Fully Convolutional Networks

UCI chess engine compiled to Javascript

Lepton is a tool and file format for losslessly compressing JPEGs by an average of 22%.

Original Apollo 11 Guidance Computer (AGC) source code for the command and lunar modules.

Caffe: a fast open framework for deep learning.

MatConvNet and Caffe repo with compact bilinear and bilinear pooling functionality added

Streisand sets up a new server running your choice of WireGuard, OpenConnect, OpenSSH, OpenVPN, Shadowsocks, sslh, Stunnel, or a Tor bridge. It also generates custom instructions for all of these s…

fizz buzz in tensorflow

Deep Residual Learning for Image Recognition

Sent2Vec encoder and training code from the paper "Skip-Thought Vectors"

Neural network visualizer

Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version

Torch implementation of ResNet from http://arxiv.org/abs/1512.03385 and training scripts

Train a deeper LSTM and normalized CNN Visual Question Answering model. This current code can get 58.16 on OpenEnded and 63.09 on Multiple-Choice on test-standard.

miniplaces2 deep residual network in neon