Weekly Machine Learning Opensource Roundup – July 26, 2018

Examples

SoC Star Modelling
A project to make a model which given an image of the night sky, identifies the constellations present in it using a CNN-classifier.

CPPN-WGAN
A series of experiments on using Compositional Pattern Producing Networks and GANs. See the two part blog posts here and here.

Toolsets

dataset-annotator
Scalable, cross-platform ion-electron app that allows the user to annotate an image dataset.

Musoq
Use SQL on various data sources

Models

Mask-RCNN
A PyTorch implementation of the architecture of Mask RCNN, serves as an introduction to working with PyTorch

NeuralTuringMachine
Tensorflow implementation of a Neural Turing Machine

Stylebank
Implementation of “StyleBank An Explicit Representation for Neural Image Style Transfer”

super-resolution-SRDPNs-tensorflow
An implementation of super-resolution based on dual-path networks. It can be used directly to reconstruct your low-resolution image to high-resolution.

GluonNLP
GluonNLP provides implementations of deep learning models in NLP, and build blocks for text data pipelines and models.

Libraries

Finetune
Scikit-learn style model finetuning for NLP. Finetune ships with a pre-trained language model from Improving Language Understanding by Generative Pre-Training” and builds off the OpenAI/finetune-language-model repository.

Parallelizing AdaBoost on Multi Core Machines using open MP in C++
AdaBoost, short for Adaptive Boosting, is a type of boosting algorithm which combines several weak classifiers to create one strong classifier. This project contains a multi-core parallel implementation of adaboost algo in C++.

torchbearer
Torchbearer is a PyTorch model training library designed by researchers, for researchers. Specifically, if you occasionally want to perform advanced custom operations but generally don’t want to write hundreds of lines of untested code then this is the library for you.

Weekly Machine Learning Opensource Roundup – July 19, 2018

Example

generating-music
A trial to create a generative model capable of composing polyphonic music. Contrary to other work in the same field, the goal was to generate music with multiple instruments playing simultaneously to cover a broader musical space.

Toolsets

speedrun
A toolkit to help you deploy and manage your machine learning experiments to be well-documented and reproducible.

UCI-ML-API
Simple API for UCI Machine Learning Dataset Repository (search, download, analyze)

snake.ai
A framework to study competing AI agents in a multi-player snake game. The multiagent nature of this game provides endless opportunities to explore RL algorithms and is also a nice way of assessing the relative performance of each methods.

Models

Compare GAN
This code was used in Are GANs Created Equal? A Large-Scale Study and in The GAN Landscape: Losses, Architectures, Regularization, and Normalization.

text-classification-models-tf
Tensorflow implementations of Text Classification Models.

Hierarchical Attention Network
Implementation of Hierarchical Attention Networks in PyTorch

Libraries

Kerasify
A small library for running trained Keras models from a C++ application

pocket-tensor
Run Keras models from a C++ application on embedded devices

LightNet*
A minimize inference neural network fork from Darknet to run simple and practical networks on lightweight mobile devices.

 

Weekly Machine Learning Opensource Roundup – July 12, 2018

Examples

Draw This.
A polaroid camera that draws cartoons. You point, and shoot – and out pops a cartoon; the camera’s best interpretation of what it saw.

word-mesh
A wordcloud/wordmesh generator that allows users to extract keywords from text, and create a simple and interpretable wordcloud, utilizing the various statistical, semantic and grammatical features of the text to inform visualization parameters.

RoboSat
Semantic segmentation on aerial and satellite imagery. Extracts features such as: buildings, parking lots, roads, water.

NeuralTitanic
View the predictions of a neural network while it is being trained on the titanic dataset.

Federalist Papers NLP
Attribution of the Federalist Papers through TF-IDF and ML

spoken language identification
Identify a spoken language using artificial intelligence (LID).

Fortnite – PUBG
Converting Fortnite texture to PUBG texture using Keras

Toolsets

lagom
A light PyTorch infrastructure to quickly prototype reinforcement learning algorithms.

PythonRobotics
A Python code collection of robotics algorithms, especially for autonomous navigation.

ElastiK Nearest Neighbors
Elasticsearch plugin for approximate K-nearest-neighbors on floating-point vectors

Models

Glow
Code for reproducing results in “Glow: Generative Flow with Invertible 1×1 Convolutions”

RelativisticGAN-Tensorflow
Simple Tensorflow implementation of RelativisticGAN

cond-shift-neurons
Implementation of Conditionally Shifted Neurons by Munkhdalai et al

DifferentiableNeuralComputer
Optimized Differentiable Neural Computer In Chainer

Switchable Normalization
A normalization technique that is able to learn different normalization operations for different normalization layers in a deep neural network in an end-to-end manner.

Libraries

TensorFlow on idris
Dependent types meets deep learning

jGeneticNeuralNet
A Java library that trains neural networks with a genetic algorithm.

Modin
Unify the way you interact with your data, a project derived from Parallelizing Pandas

Weekly Machine Learning Opensource Roundup – July 5, 2018

Examples

Is this loss? A Loss.jpg Detector
Source for the highly popular Android application known as “Is this loss?”

T2F
Text to face generation using Deep Learning. This project combines two of the recent architectures StackGAN and ProGAN for synthesizing faces from textual descriptions.

Discover Feature Relationships
Attempt to discover 1D relationships between all columns in a DataFrame using scikit-learn (RandomForests) and standard correlation tests (Pearson, Spearman and Kendall via Pandas).

Toolsets

HOTTBOX
Higher Order Tensors Toolbox for tensor decompositions, statistical analysis, visualisation, feature extraction, regression and non-linear classification of multi-dimensional data.

Enso
An Open Source Library for Benchmarking Embeddings + Transfer Learning Methods

MuViLab
A manual annotation tool to help you labelling videos for computer vision, machine learning and AI applications

Palisade
Scalable Data Policy Management and Enforcement

Models

WorldModels
Full World Models Implementation in Chainer

sg2im
Code for “Image Generation from Scene Graphs”, Johnson et al, CVPR 2018

darts
Differentiable architecture search for convolutional and recurrent networks

HNATT
Train and visualize Hierarchical Attention Networks

Guided Attention Inference Network
An implementation of Guided Attention Inference Network (GAIN) presented in Tell Me Where to Look(CVPR 2018).

Libraries

tfjsx
Tensorflow.js + React JSX = The ML API you never asked for

Smart-Fruit
A Python schema-based machine learning library

Framework

MACE
Mobile AI Compute Engine (or MACE for short) is a deep learning inference framework optimized for mobile heterogeneous computing platforms

Weekly Machine Learning Opensource Roundup – June 28, 2018

Examples

2018 MachineLearning Lectures ESA
Machine Learning Lectures at the European Space Agency (ESA) in 2018

Financial Times Visual Vocabulary
A poster and web site to assist designers and journalists to select the optimal symbology for data visualisations, by the Financial Times Visual Journalism Team.

RobustML
The goal of this website is to serve as a community-run hub for learning about robust ML. This list contains proposed white-box defenses to adversarial examples, along with third-party analyses / security evaluations.

Tracking Progress in Natural Language Processing
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

Deep Learning for Natural Language Processing
Organized Resources for Deep Learning in Natural Language Processing

Mortality Explorer
Tool for querying US mortality data, modeled in Neo4J with React/GraphQL interface (GRAND stack)

ATARI GAN
Generating Atari images using Generative Adversarial Networks

EGADS Java Library
Extensible Generic Anomaly Detection System is an open-source Java package to automatically detect anomalies in large scale time-series data. EGADS is meant to be a library that contains a number of anomaly detection techniques applicable to many use-cases in a single package with the only dependency being Java.

NCRF
Cancer metastasis detection with neural conditional random field (NCRF)

Toolsets

Jsonnet
The data templating language

TagUI
A CLI tool for digital process automation (RPA). It is maintained by AI Singapore, a government-funded initiative to build local artificial intelligence capabilities. To start, check out above tutorial, slides, or video.

Models

SNIPER
An efficient multi-scale training approach for instance-level recognition tasks like object detection and instance-level segmentation

scalable_agent
A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.

choicenet
TensorFlow Implementation of ChoiceNet on regression tasks

Baselines incl. RUDDER
RUDDER for ATARI games with delayed rewards in OpenAI Baselines package

Libraries

sqlite-parquet-vtable
A SQLite vtable extension to read Parquet files

Menoh
fast DNN inference library with multiple programming language support

hasktorch
A library for tensors and neural networks in Haskell. It is an independent open source community project which leverages the core C libraries shared by Torch and PyTorch.

ImageAI
A python library built to empower developers to build applications and systems with self-contained Computer Vision capabilities

distiller
A Python package for neural network compression research to reduce the memory footprint of a neural network, increase its inference speed and save energy

 

Weekly Machine Learning Opensource Roundup – June 21, 2018

Examples

Interactive Machine Learning List
A collaborative list of interactive Machine Learning, Deep Learning and Stats websites

MaH-browser
Labels image from unsplash.com in Firefox & Chrome – using MobileNet on Tensorflow.Js

Toolsets

TFaaS
TensorFlow as a Service, a general purpose framework to serve TF models.

Box-X
Tool-box for efficient build and debug in Python. Especially for Scientific Computing and Computer Vision.

MonoCorpus
A notepad for software and machine learning

HDFS Client for Go
A native go client for HDFS

dlwin
GPU-accelerated Deep Learning on Windows 10 native (Keras/Tensorflow/CNTK/MXNet and PyTorch)

DataDefender
Sensitive Data Management: Data Discovery and Anonymization toolkit

Metacar
A reinforcement learning environment for self-driving cars in the browser.

Kepler.gl
A data-agnostic, high-performance web-based application for visual exploration of large-scale geolocation data sets

Models

Relation Networks for Object-Detection
The official implementation for Relation Networks for Object Detection based on MXNet

decaNLP
The Natural Language Decathlon: A Multitask Challenge for NLP

DensePose
A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body

Lda2vec in Tensorflow
Tensorflow 1.5 implementation of Chris Moody’s Lda2vec, adapted from @meereeum

OpenAI’s Transformer Language Model in PyTorch
A PyTorch implementation of OpenAI’s finetuned transformer language model with a script to import the weights pre-trained by OpenAI

Zero-shot GCN in TensorFlow
A re-implementation of the zero-shot classification in ImageNet in the paper Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs.

Libraries

dbx
A fast, easy-to-use database library for R. Supports Postgres, MySQL, SQLite, and more.

jplow
Java tools and data structures for working with Snowplow events

SLM-Lab
Modular Deep Reinforcement Learning framework in PyTorch.

tensorflow-haskell-deptyped
Reexporting TensorFlow Haskell with dependent typed functions

NVIDIA DALI
A library containing both highly optimized building blocks and an execution engine for data pre-processing in deep learning applications