Weekly Machine Learning Opensource Roundup – Aug. 23, 2018

Examples

Food Recipe CNN
Deep Learning food image recognition system for cooking recipe retrieval

Retrain MobileNet for the web
Retrain a MobileNet V1 or V2 model and use it in the browser with TensorFlow.js

ENV400 Assignment
Assignment for ENV-400 (Air Pollution and Climate Change) Masters course at EPFL

Deep Learning Coursera
Projects from the Deep Learning Specialization from deeplearning.ai provided by Coursera

Models

vid2vid
Pytorch implementation of our method for high-resolution (e.g. 2048×1024) photorealistic video-to-video translation.

PolygonRNN++
PyTorch training/tool code for Polygon-RNN++ (CVPR 2018)

relational-rnn-pytorch
An implementation of DeepMind’s Relational Recurrent Neural Networks in PyTorch.

MSG-GAN
Multi-Scale Gradients GAN (Architecture inspired from ProGAN but doesn’t use layer-wise pretraining)

Libraries

DoWhy
A Python library based on a unified language for causal inference that makes it easy to estimate causal effects. DoWhy combines causal graphical models and potential outcomes frameworks.

TransmogrifAI
TransmogrifAI (pronounced trăns-mŏgˈrə-fī) is an AutoML library for building modular, reusable, strongly typed machine learning workflows on Spark with minimal hand tuning

LocustDB
Massively parallel, high performance analytics database that will rapidly devour all of your data

Petastorm
A library enabling the use of Parquet storage from Tensorflow, Pytorch and other Python based ML training frameworks

libartificial
A small pure C shared library with ML/nonparametrix algorithms for researchers and developers

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