Weekly Machine Learning Opensource Roundup – Jan. 24, 2019

Examples

Machine-Learning-with-Python
Small scale machine learning projects to understand the core concepts

How To Make Your Data Analysis Notebooks More Reproducible
A guide to make your data analysis more reproducible.

end-to-end-lead-scoring
An end-to-end enterprise-grade example of working a data science problem.

profanity-check
A fast, robust Python library to check for offensive language in strings.

Generative Models Tutorial with Demo
Popular GANs Architectures, Auto-Regressive Models, Important Generative Model Papers, Courses, etc.

Toolsets

The PyTorch-Kaldi Speech Recognition Toolkit
A project for developing DNN/RNN hybrid speech recognition systems

TeleGrad
A Telegram bot to monitor and control deep learning experiments

Libraries

Mars
A tensor-based unified framework for large-scale data computation.

LASER
A library to calculate and use multilingual sentence embeddings.

Weekly Machine Learning Opensource Roundup – Jan. 17, 2019

Example

Desnapify
A deep convolutional generative adversarial network (DCGAN) trained to remove Snapchat filters from selfie images.

Toolsets

NSFW Data Scrapper
Collection of scripts to aggregate image data for the purposes of training an NSFW Image Classifier

Decision Tree Visualization
A python library for decision tree visualization and model interpretation.

Models

dnc
Implementation of “Differentiable Neural Computer” as close as possible to the description in the paper

Padam-Tensorflow
Reproducing the paper “PADAM: Closing The Generalization Gap of Adaptive Gradient Methods In Training Deep Neural Networks” for the ICLR 2019 Reproducibility Challenge

Libraries

Delira – Deep Learning in Radiology
Lightweight framework for fast prototyping and training deep neural networks in medical imaging

NeuralVerification.jl
Methods to soundly verify deep neural networks

 

Weekly Machine Learning Opensource Roundup – Jan. 10, 2019

Examples

DeepTraffic
A deep reinforcement learning competition, part of the MIT Deep Learning series.

Sentence Classification
Sentence Classifications with Neural Networks

neural-machine-translation-from-scratch
Machine Translation from Scratch Using Pytorch

Machine Translation Reading List
A machine translation reading list maintained by Tsinghua Natural Language Processing Group

MagicBrush
Using Neural Style Transfer to convert an interactive painting to a masterpiece in real time.

NEUZZ
neural network assisted fuzzer

deep-learning-comprehensive-resources
All You Need to Know About Deep Learning – A kick-starter

Toolsets

turkey
turkey lets you easily create a web UI on Amazon Mechanical Turk to crowd-source image annotation data

COCO Annotator
Web-based image segmentation tool for object detection and localization

benderopt
A Black Box Hyperparameters Optimization platform

flatten-sstabledump
A utility that unwraps Apache Cassandra’s `sstabledump` JSON array output to multiple small JSON objects

Lingvo
An experimental framework for building neural networks in Tensorflow, particularly sequence models.

Models

EdgeConnect
Generative Image Inpainting with Adversarial Edge Learning

InstaGAN
PyTorch implementation of “InstaGAN: Instance-aware Image Translation” (ICLR 2019)

NMFADMM
A sparsity aware implementation of “Alternating Direction Method of Multipliers for Non-Negative Matrix Factorization with the Beta-Divergence” (ICASSP 2014).

TRAttack
Trust Region Based Adversarial Attack

sketch_rnn_keras
Keras implementation of Sketch RNN

Generating-Devanagari-Using-DRAW
PyTorch implementation of “DRAW: A Recurrent Neural Network For Image Generation”

ganless-hd
The basic idea is to utilize a U-Net, modified perceptual loss (pearson instead of MAE), learned basis functions, and “mean teacher” training in order to synthesize images of high quality without the normal troubles of training a GAN.

Libraries

TensorStream
A ground-up and standalone reimplementation of TensorFlow for ruby. Comes with a pure ruby and OpenCL opcode evaluator

Crossbow
A Multi-GPU Deep Learning System for Training with Small Batch Sizes

 

Weekly Machine Learning Opensource Roundup – Dec. 27, 2018

Examples

christmAIs
Text to abstract art generation for the holidays!

Data Science Cheatsheets
List of Data Science Cheatsheets to rule the world

tetris_mcts
Learning to play Tetris with Monte Carlo Tree Search and Temporal Difference Learning

Reinforcement Learning (RL) Tutorial
Reinforcement Learning Tutorial with Demo: DP (Policy and Value Iteration), Monte Carlo, TD Learning (SARSA, QLearning), Function Approximation, Policy Gradient, DQN, Imitation, Meta Learning, Papers, Courses, etc..

GNNPapers
Must-read papers on GNN (Graph Neural Network)

Toolset

dolphinbeat
An application that pulls MySQL binlog, parses binlog and pushs incremental update data into different sinks, for example, kafka.

Models

Super-SloMo
PyTorch implementation of Super SloMo by Jiang et al.

3D Convolutional Neural Networks for Speaker Verification
This repository contains the Pytorch code release for our paper titled as “Text-Independent Speaker Verification Using 3D Convolutional Neural Networks”.

FaceBoxes
A CPU Real-time Face Detector with High Accuracy, IJCB, 2017

PointNet-PyTorch
A PyTorch implementation of PointNet, with comprehensive experiments.

Libraries

pennylane
PennyLane is a cross-platform Python library for quantum machine learning, automatic differentiation, and optimization of hybrid quantum-classical computations

flashlight
A fast, flexible machine learning library written entirely in C++ from FAIR Speech Team and the creators of Torch and DeepSpeech to support both CPU and GPU backends for maximum efficiency and scale.

torchgan
Research Framework for easy and efficient training of GANs based on Pytorch

privacy
Library for training machine learning models with privacy for training data

nevergrad
A Python toolbox for performing gradient-free optimization

 

Weekly Machine Learning Opensource Roundup – Dec. 20, 2018

There are three noteworthy projects in this week!

Toolset

FacebookResearch PyText
A deep-learning based natural language modeling framework built on PyTorch. PyText addresses the often-conflicting requirements of enabling rapid experimentation and of serving models at scale.

Libraries

Deep Graph Library (DGL)
A Python package that interfaces between existing tensor libraries and data being expressed as graphs. It makes implementing graph neural networks (including Graph Convolution Networks, TreeLSTM, and many others) easy while maintaining high computation efficiency.

Microsoft Trill
A high-performance one-pass in-memory streaming analytics engine from Microsoft Research. It can handle both real-time and offline data, and is based on a temporal data and query model.

Weekly Machine Learning Opensource Roundup – Dec. 13, 2018

Examples

ML World Map
Visual Machine Learning Graph of all arXiv papers and researchers

Awesome Sentence Embedding
A curated list of pretrained sentence(and word) embedding models.

AmbiverseNLU
The multilingual Ambiverse Natural Language Understanding suite (AmbiverseNLU) by Max Planck Institute for Informatics combines a number of state-of-the-art components for language understanding tasks

HE Transformer for nGraph
Homomorphic encryption is a form of encryption that allows computation on encrypted data, and is an attractive remedy to increasing concerns about data privacy in the field of machine learning.

(This is not intended to be a production-ready product, but rather a research tool)

Toolset

trickster
Library and experiments for attacking machine learning in discrete domains using graph search.

Models

loss-landscape
Code for visualizing the loss landscape of neural nets

PartialConv Tensorflow
Simple Tensorflow implementation of “Partial Convolution based Padding” (partialconv)

Libraries

JAX: Autograd and XLA
GPU- and TPU-backed NumPy with differentiation and JIT compilation.

TensorFlow Ranking
Learning to Rank in TensorFlow

matrixprofile-ts
An open source Python time series library for motif discovery and anomaly detection using Matrix Profile, a highly-performant, robust method of identifying patterns and anomalies present in time-series data.

Logisland
An event mining scalable platform designed to process and patterns mining a high throughput of complex event at scale