An Open Source Machine Learning Framework for Everyone

Tesseract Open Source OCR Engine (main repository)

A library for efficient similarity search and clustering of dense vectors.

Caffe: a fast open framework for deep learning.

Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit

GDAL is an open source MIT licensed translator library for raster and vector geospatial data formats.

MITIE: library and tools for information extraction

Collective communications library with various primitives for multi-machine training.

CBOR C++ serialization library

Using latent Dirichlet allocation (LDA) in Apache Lucene

Visual Exploration of New York City Taxi Trips

Object Segmentation (NIPS 2014)

mirror of google code version for git updates

Unreal Engine 4 integraton of Apache Tika to detect and extract metadata and text from over a thousand different file types (such as PPT, XLS, and PDF).

A Python tool for Speaker, Language, and Gender Recognition (SLGR) and general meta-data extraction.

CMU Foreground/Background Similarity Server from DARPA MEMEX

An implementation of LSH that reads features from disk

compute different kinds of features and generate matching graph