Weekly Machine Learning Opensource Roundup – Apr. 5, 2018

Examples

Parkinsons AI
Detect Parkinsons using XGBoost and Neural Networks

Five Video Classification Methods
Code that accompanies my blog post outlining five video classification methods in Keras and TensorFlow

Imagination Augmented Agents
Building Agents with Imagination: pytorch easy-to-follow step-by-step tutorial

Toolset

ANN Visualizer
A python library for visualizing Artificial Neural Networks (ANN)

Models

DEXTR-PyTorch
Deep Extreme Cut in PyTorch

keras-deeplab-v3-plus
Keras implementation of Deeplab v3+ with pretrained weights

enas
TensorFlow Code for paper “Efficient Neural Architecture Search via Parameter Sharing”

Libraries

TensorFlow Hub
A library for transfer learning by reusing parts of TensorFlow models.

TensorFlow.js
A WebGL accelerated, browser based JavaScript library for training and deploying ML models.

TensorFlow Model Analysis
A library for evaluating TensorFlow models. It allows users to evaluate their models on large amounts of data in a distributed fashion, using the same metrics defined in their trainer

DL-Text
Text pre-processing modules for deep learning for Keras and Tensorflow

Mittens
A fast implementation of GloVe, with optional retrofitting


Like to add your project? tweet @stkim1!

Weekly Machine Learning Opensource Roundup – Mar. 29, 2018

Examples

RL Adventure
Pytorch easy-to-follow step-by-step Deep Q Learning tutorial with clean readable code

PyTorch Template
A simple template project using PyTorch which can be modified to fit many deep learning projects

GAN Numpy
An implementation of a simple vanilla GAN model that generates a subset of MNIST numbers (single number recommended) to help MLP and GAN study

Hands on NLTK Tutorial
A hands-on NLTK tutorial in the form of Jupyter notebooks

Stats 337: Readings in Applied Data Science
Readings in a small discussion-oriented applied data science class available to Stanford students in Spring 2018

Open Computational Neuroscience Resources
A publicly-editable collection of open computational neuroscience resources

Porcupine
A self-service, highly-accurate, and lightweight wake word detection engine. It enables developers to build always-listening voice-enabled applications/platforms

Toolsets

Matchbox
Write PyTorch code at the level of individual examples, then run it efficiently on minibatches.

Sparklens
A performance tuning tool for Apache Spark with built-in Spark Scheduler simulator

Netron
Visualizer for deep learning and machine learning models

DALEX
Descriptive mAchine Learning EXplanations

Models

BicycleGAN
Tensorflow implementation of the NIPS paper “Toward Multimodal Image-to-Image Translation”

Neural coref v2.0
State-of-the-art coreference resolution based on neural nets and spaCy

Stochastic Weight Averaging (SWA)
Stochastic Weight Averaging in PyTorch

Libraries

NVVL (NVIDIA Video Loader)
A library that uses hardware acceleration to load sequences of video frames to facilitate machine learning training

lintel
A Python module to decode video frames directly, using the FFmpeg C API.

infer
Use TensorFlow models in Go to evaluate Images


Like to add your project? tweet @stkim1!

Weekly Machine Learning Opensource Roundup – Mar. 22, 2018

Examples

Sketch Code
Keras model to generate HTML code from hand-drawn website mockups. Implements an image captioning architecture to drawn source images.

Fast Pandas
Benchmark for different operations in pandas against various dataframe sizes.

Tarkin
A tool for anomaly detection over streaming data based on sentiment analysis

Nexus
Experimental typesafe deep learning in Scala

Verilog Generator of Neural Net Digit Detector for FPGA
A project training and converting neural net in verilog HDL to detect dark digits on light background

Toolsets

dvc
Git for data scientists – manage your code and data together

Kafka Elasticsearch Injector
Golang app to read records from a set of kafka topics and write them to an elasticsearch cluster

mAP
This code will evaluate the performance of your neural net for object recognition using the mean Average Precision (mAP).

Live Loss Plot
Live training loss plot in Jupyter Notebook for Keras, PyTorch and others

LabNotebook
LabNotebook is a tool that allows you to flexibly monitor, record, save, and query all your machine learning experiments.

Simple TensorFlow Serving
Generic and easy-to-use serving service for machine learning models

Models

Word2Bits
Quantized word vectors that take 8x-16x less storage/memory than regular word vectors

Undreamt
Unsupervised Neural Machine Translation

deep-person-reid
Pytorch implementation of deep person re-identification approaches

Library

nGraph
An open source C++ library, compiler and runtime for Deep Learning frameworks


Like to add your project? tweet @stkim1!

Weekly Machine Learning Opensource Roundup – Mar. 15, 2018

Examples

Machine Learning Basics
Plain python implementations of basic machine learning algorithms

Open Avalanche Project
Open source project to bring data and ml to avalanche forecasting

Toolsets

word2vec graph
This visualization builds graphs of nearest neighbors from high-dimensional word2vec embeddings.

Chatito
Generate datasets for slot filling NLU chatbots in a breeze using a simple DSL!

ServeIt
Simple API serving for Python ML models

ToastUI Chart
Beautiful chart for data visualization.

factorMerger
A Set of Tools to Support Adaptive Post-Hoc Fusing of Groups

Models

indrnn
TensorFlow implementation of Independently Recurrent Neural Networks

improved-wgan-pytorch
Improved Training of Wasserstein GANs in Pytorch

BicycleGAN-pytorch
Pytorch implementation of BicycleGAN with implementation details

TFSegmentation
RTSeg: Real-time Semantic Segmentation Comparative Study

Libraries

stxxl
Standard Template Library for Extra Large Data Sets

DataflowKit
Dataflow Kit extracts structured data from web sites


Like to add your project? tweet @stkim1!

Weekly Machine Learning Opensource Roundup – Mar. 8, 2018

Examples

TrufflePig
A Steemit Curation Bot based on Natural Language Processing and Machine Learning.

Cat DCGAN
A DCGAN that generate Cat pictures

Sentence Space
Generating gradients, exploring neighborhoods.

Toolsets

NMT-Keras
Neural Machine Translation with Keras (Theano/Tensorflow)

MMdnn
A set of tools to help users inter-operate among different deep learning frameworks

Models

NeuroSAT
An experimental SAT solver that is learned using single-bit supervision only

PyTorch Dilated RNN
PyTorch implementation of Dilated Recurrent Neural Networks (DilatedRNN)

TensorFlow ImageNet
High performance (hopefully!) training of ImageNet TensorFlow Models – Training and SOTA checkpoints

PyTorch i-RevNet
Pytorch implementation of i-RevNets, Deep Invertible Networks

Siamese-triplet
Siamese and triplet networks with online pair/triplet mining in PyTorch

Libraries

featuremill
general-purpose fast, stateless, and deterministic feature extractor writting in golang for use in machine learning

PyToune
A Keras-like framework for PyTorch and handles much of the boilerplating code needed to train neural networks

Snips NLU
Snips Python library to extract meaning from text

Lore
Lore makes machine learning approachable for Software Engineers and maintainable for Machine Learning Researchers

 


Like to add your project? tweet @stkim1!

Weekly Machine Learning Opensource Roundup – Mar. 1, 2018

Examples

Paradigms of Artificial Intelligence Programming (1992)
The repository for Peter Norvig’s book and Lisp code

Capsnet – Traffic sign classifier
A Tensorflow implementation of CapsNet(Capsules Net) applied on german traffic sign dataset

Sklearn Interpretable Tree
Simplified tree-based classifier and regressor for interpretable machine learning (scikit-learn compatible)

Toolsets

DeepPavlov
An open source library for building end-to-end dialog systems and training chatbots (early alpha release).

CheXNet Keras
This project is a tool to build CheXNet-like models, written in Keras.

Models

Handwriting Synthesis
Implementation of the handwriting synthesis experiments in the paper Generating Sequences with Recurrent Neural Networks by Alex Graves

MADDPG
An implementation of Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments.

One Pixel Attack in Keras
Keras reimplementation of “One pixel attack for fooling deep neural networks” using differential evolution on cifar10

Libraries

Aurora
Minimal Deep Learning library is written in Python/Cython/C++ and Numpy/CUDA/cuDNN.

Magnitude
A feature-packed Python package and vector storage file format for utilizing vector embeddings in machine learning models in a fast, efficient, and simple manner


Like to add your project? tweet @stkim1!

Weekly Machine Learning Opensource Roundup – Feb. 15, 2018

Examples

3D Machine Learning
A collection of paper, code, and dataset for 3D Machine Learning

Machine Learning Links and Lessons Learned
A list of lessons learned, best practices, and study links of machine learning

Deep Reinforcement Learning
The learner is not told which actions to take, but instead must discover which actions yield the most reward by trial and error.

DeepTraffic3D
A 3D view the DeepTraffic project as part of MIT Deep Learning for Self-Driving Cars

Convolution Visualizer
This interactive visualization demonstrates how various convolution parameters affect shapes and data dependencies between the input, weight and output matrices.

CapsNet Visualization
A visualization of the CapsNet layers to better understand how it works

Toolsets

Tensor Comprehensions
Tensor Comprehensions (TC) is a domain specific language to express machine learning workloads. It is a fully-functional C++ library to automatically synthesize high-performance machine learning kernels using Halide, ISL and NVRTC or LLVM. TC additionally provides basic integration with Caffe2 and pybind11 bindings for use with python.

ARM Systolic CNN AcceLErator Simulator (SCALE Sim)
A CNN accelerator simulator that provides cycle-accurate timing, power/energy, memory bandwidth and traces results for a specified accelerator configuration and neural network architecture

SHAP (SHapley Additive exPlanations)
A unified approach to explain the output of any machine learning model

Marija
Data exploration and visualisation for Elasticsearch.

Models

DeepType
OpenAI’s latest approach to learning symbolic structures from data allows them to discover a set of task specific constraints on a neural network in the form of a type system, to guide its understanding of documents, and obtain state of the art accuracy at recognizing entities in natural language.

Attention-Based Guided Structured Sparsity of Deep Neural Networks
An attention mechanism that simultaneously controls the sparsity intensity and supervised network pruning by keeping important information bottlenecks of the network to be active.

Weakly Supervised Segmentation with TensorFlow
The idea behind weakly supervised segmentation is to train a model using cheap-to-generate label approximations (e.g., bounding boxes) as substitute/guiding labels for computer vision classification tasks that usually require very detailed labels.

Prototypical Networks for Few shot Learning in PyTorch
Simple alternative Implementation of Prototypical Networks for Few Shot Learning in Pytorch


Like to add your project? tweet @stkim1!