Weekly Machine Learning Opensource Roundup – Jan. 10, 2018

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

 

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s