An Open Source Machine Learning Framework for Everyone

Protocol Buffers - Google's data interchange format

LevelDB is a fast key-value storage library written at Google that provides an ordered mapping from string keys to string values.

Caffe: a fast open framework for deep learning.

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

Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive lea…

C-based/Cached/Core Computer Vision Library, A Modern Computer Vision Library

DyNet: The Dynamic Neural Network Toolkit

High performance, easy-to-use, and scalable machine learning (ML) package, including linear model (LR), factorization machines (FM), and field-aware factorization machines (FFM) for Python and CLI …

Automatically exported from code.google.com/p/smhasher

Deep Learning API and Server in C++14 support for PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE

Library for factorization machines

Knowledge Graph Embeddings including TransE, TransH, TransR and PTransE

LINE: Large-scale information network embedding

GraphChi's C++ version. Big Data - small machine.

Faster Recurrent Neural Network Language Modeling Toolkit with Noise Contrastive Estimation and Hierarchical Softmax

Solutions of LeetCode Online Judge

Caffe implementation of our multi-scale object detection framework

Knowledge Base Embedding

No voice but big deal.

GIZA++ is a statistical machine translation toolkit that is used to train IBM Models 1-5 and an HMM word alignment model. This package also contains the source for the mkcls tool which generates th…

Collaborative modeling for recommendation. Implements variational inference for a collaborative topic models. These models recommend items to users based on item content and other users' ratings.

Code release for DeepBox paper in ICCV 2015

Collaborative Denoising Auto-Encoder for Top-N Recommender Systems

C++ code for the RDIS algorithm from "Recursive Decomposition for Nonconvex Optimization." Friesen and Domingos, IJCAI 2015.

A collection of adaptive sparse multi-scale solvers for optimal transport and related optimization problems.

Communication-Minimizing 2D Convolution in GPU Registers

Bridging Items and Language: A Transition Paradigm for Large Language Model-Based Recommendation (KDD'24)