Weekly Machine Learning Opensource Roundup – Jan. 18, 2018


Migrating to Python 3 with pleasure
A short guide on features of Python 3 for data scientists

Production Data Science
Workflow for collaborative data science aimed at production

Computer Vision Basics with Python Keras and OpenCV
Full tutorial of computer vision and machine learning basics with OpenCV and Keras in Python.

Pirate AI
PirateAI trains autonomous agents in a simulated environment on Unity, Hyperopt, and Keras

CapsNet Tensorflow
Testing Capsule Network on various datasets

TVM Mali
Optimizing Mobile Deep Learning on ARM GPU with TVM


Spinzero – Jupyter Notebook Theme
A minimal Jupyter Notebook theme

Label Maker
Data Preparation for Satellite Machine Learning

A platform to visualize the deep learning process.

Apache Sentry
A granular, role-based authorization module for Hadoop. Sentry provides the ability to control and enforce precise levels of privileges on data for authenticated users and applications on a Hadoop cluster


TensorFlow implementation of CipherGAN

Machine Learning-Based Predictive Modelling of CRISPR/Cas9 guide efficiency. Microsoft Research presents a state-of-the art predictive approach to modeling which RNA guides will effectively perform a gene knockout by way of the CRISPR/Cas9 system.

Gradient Checkpointing
Training very deep neural networks requires a lot of memory. Using the tools in this package, developed jointly by Tim Salimans and Yaroslav Bulatov, you can trade off some of this memory usage with computation to make your model fit into memory more easily.


.NET bindings for native numerical computing

Simple Node.js API for robust face detection and face recognition.

A GPU-backed numpy-like infrastructure for scientific computing in JavaScript. Propel runs both in the browser and natively from Node.

A light-weight column-oriented data processing engine based on a new data model and is an alternative to conventional SQL-like languages, map-reduce and other set-oriented approaches

Like to add your project? tweet to @stkim1!

Weekly Machine Learning Opensource Roundup – Jan. 11, 2018


Active Learning Playground
A python module for experimenting with different active learning algorithms

Julia DataFrames Tutorial
A tutorial on Julia DataFrames package

Simple Adversarial Examples
Repo of simple adversarial examples on vanilla neural networks trained on MNIST

Screenshot to code in Keras
A neural network that transforms a screenshot into a static website


Tensorlang, a differentiable programming language based on TensorFlow

The Spiral Language
A statically typed functional language compiling to F# and Cuda

Theres an AI for That
Web based tools for computer vision data preparation and deep learning based object detection built on top of tensorflow object detection.

Convolutional Neural Network Visualizations
Pytorch implementation of convolutional neural network visualization techniques

Pandas Profiling
Create HTML profiling reports from pandas DataFrame objects

An interactive grid for sorting, filtering, and editing DataFrames in Jupyter notebooks


Optic Nerve CNN
Code repository for a paper “Optic Disc and Cup Segmentation Methods for Glaucoma Detection with Modification of U-Net Convolutional Neural Network”

PyTorch ZSSR
PyTorch implementation of “Zero-Shot” Super-Resolution using Deep Internal Learning

A Clearer and Simpler Synchronous Advantage Actor Critic (A2C) Implementation in TensorFlow

Tacotron PyTorch
Pytorch implementation of Tacotron


Modular Active Learning framework for Python3

A Python data validation library.

An in-memory columnar analytical data store

Like to add your project? tweet to @stkim1!

Weekly Machine Learning Opensource Roundup – Jan. 4, 2018


Simple SMT solver

Susi Server
Personal Assistants SUSI Artificial Intelligence Backend for Chat Bots

Images to OSM
Use TensorFlow, Bing, and OSM to find features in satellite images for fun.


DM Control
The DeepMind Control Suite and Control Package


Facebook AI Research Automatic Speech Recognition Toolkit

Skip Thoughts
An implementation of Skip-Thought Vectors in PyTorch

Noisy Natural Gradient
Pytorch Implementation of paper “Noisy Natural Gradient as Variational Inference”


A Fast SVM Library on GPUs and CPUs

Penalized Sparse Learning Solver – Unleash the Power of Nonconvex Penalty


Like to add your project? tweet to @stkim1!

Weekly Machine Learning Opensource Roundup – Dec. 28, 2017


Twitter Sentiment Analysis
Sentiment analysis on tweets using Naive Bayes, SVM, CNN, LSTM, etc.

Penn Machine Learning Benchmarks
A large, curated repository of benchmarks for evaluating supervised machine learning algorithms.

NP-Hard Deep Reinforcement Learning
Combinatorial optimization with DL/RL in PyTorch

AC-GAN Biased
Experiments verifying that AC-GAN downsamples points near decision boundary

Going Deeper
Infinite Deep Neural Networks

Boring Detector
State-of-the-art detector of Boring hats in images and videos.


A PyTorch implementation of the agent presented in Playing FPS Games with Deep Reinforcement Learning.

A javascript library that extends D3.js to enable fast and beautiful visualizations.

Jupyter Vim Binding
Jupyter meets Vim. Vimmer will fall in love.


Bottom-Up Attention VQA
An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge.

A partial implementation of the Rainbow agent in PyTorch. Rainbow is a deep Q learning based agent that combines a bunch of existing techiques such as dueling dqn, distributional dqn, etc.

Implementation of paper “GibbsNet: Iterative Adversarial Inference for Deep Graphical Models” in PyTorch


A library for Multilingual Unsupervised or Supervised word Embeddings

A fast, ergonomic and portable tensor library in Nim with a deep learning focus

Face detection library for the Rust programming language

An open source C++ face recognition engine, which can run on CPU with no third-party dependence


The Koç University deep learning framework implemented in Julia by Deniz Yuret and collaborators. It supports GPU operation and automatic differentiation using dynamic computational graphs for models defined in plain Julia.

Looking into adding your repo? tweet to @stkim1!

Weekly Machine Learning Opensource Roundup – Dec. 21, 2017


A workshop for scientific computing in Python.

1.4 Billion Text Credentials Analysis
Deep Learning model to analyze a large corpus of clear text passwords.

From neural networks to the Category of composable supervised learning algorithms in Scala with compile-time matrix checking based on singleton-types

AICamera Style Transfer
Neural Style Transfer with Caffe2 on your Android phone


Re-usable, easy interface JavaScript chart library based on D3 v4+

Arcade Learning Environment
A simple object-oriented framework that allows researchers and hobbyists to develop AI agents for Atari 2600 games

Data visualization library for creating interactive graphs and dashboards for bioinformatics etc.


A Deep Learning Approach for Password Guessing

Subword NMT
Subword Neural Machine Translation

Transformer TF
TensorFlow implementation of ‘Attention Is All You Need (2017. 6)’


LightNet provides a simple and efficient Python interface to DarkNet

spaCy models
Models for the spaCy Natural Language Processing (NLP) library

A bare-bones TensorFlow framework for Bayesian deep learning and Gaussian process approximation

A python library for automated feature engineering

Neural Machine Translation Framework in PyTorch

Chainer Chemistry
A Library for Deep Learning in Biology and Chemistry


Looking into adding your repo? tweet to @stkim1!

Weekly Machine Learning Opensource Roundup – Dec. 14, 2017


NIPS 2017
Here’s a list of resources and slides of all invited talks, tutorials and workshops at Neural Information Processing Systems (NIPS) 2017 conference.

Keras Image Captioning
An implementation of image captioning in Keras

Scene Scoop
A tool to describe the content of videos and suggest similar scenes in other videos/films.

Sentiment Analysis on Twitter data
Sentiment analysis over twitter data (deep learning) in Python

Here Is Wally
Deep learning project that solves Where’s Waldo puzzles by finding Waldo in an image


Extract Keywords from sentence or Replace keywords in sentences, based on the FlashText algorithm.

FacebookResearch House3D
A Realistic and Rich 3D environment which consists of thousands of indoor scenes equipped with a diverse set of scene types, layouts and objects sourced from the SUNCG dataset.


An Unconditional End-to-End Neural Audio Generation Model


A scikit-learn compatible neural network library that wraps PyTorch

A high-level library to help with training neural networks in PyTorch.

A research platform for many-agent reinforcement learning. Unlike previous research platforms that focus on reinforcement learning research with a single agent or only few agents, MAgent aims at supporting reinforcement learning research that scales up from hundreds to millions of agents.

Looking into adding your repo? tweet to @stkim1!

Weekly Machine Learning Opensource Roundup – Dec. 7, 2017


Stanford DAWNBench
An End-to-End Deep Learning Benchmark and Competition

Neural Network in JavaScript with Deeplearn.js
Using a Neural Network to choose a accessible font color based on a background color.

Cat Classifier
An experiment to visualize a trained deep neural network as activation plots

TSNE Embedding Visualisation
A Simple and easy to use way to Visualise Embeddings!


OpenAI Blocksparse
Efficient GPU kernels for block-sparse matrix multiplication and convolution

Stream Reactor
Streaming reference architecture for ETL with Kafka and Kafka-Connect

An automated adversary emulation system

MatchZoo is a toolkit for text matching. It was developed to facilitate the designing, comparing, and sharing of deep text matching models.

Google DeepVariant
An analysis pipeline that uses a deep neural network to call genetic variants from next-generation DNA sequencing data.

HoME Platform
A Household Multimodal Environment is a platform for artificial agents to learn from vision, audio, semantics, physics, and interaction with objects and other agents, all within a realistic context.


CNN-DCNN text autoencoder
Implementations of the models in the paper “Deconvolutional Paragraph Representation Learning” by Yizhe Zhang, Dinghan Shen, Guoyin Wang, Zhe Gan, Ricardo Henao and Lawrence Carin, NIPS 2017

Synthesizing and manipulating 2048×1024 images with conditional GANs

PyTorch Unsupervised Sentiment Discovery
Unsupervised Language Modeling at scale for robust sentiment classification


Probabilistic Torch is library for deep generative models that extends PyTorch

Gradient based receptive field estimation for Convolutional Neural Networks

AI on Hadoop

A lightweight approximate Nearest Neighbor library which runs faster even with large datasets

Nvidia Cutlass
CUDA Templates for Linear Algebra Subroutines


Looking into adding your repo? tweet to @stkim1!