DyNet

The Dynamic Neural Network Toolkit

Graph

Dynamic Computational Graph

DyNet builds its computational graph on the fly. This makes variable-input and variable-output models simple to implement with high performance.

Batch

Dynamic Operation Batching

DyNet automatically reorganizes operations into batches for maximum performance, without requiring the developer to do so.

Hex

Ideal for Complex Structures

DyNet is well-suited for natural language processing, graph structures, reinforcement learning, and other complex state spaces.

Get Started

Tutorials

Book

Learn how to use DyNet

Examples

Grid

Browse projects built using DyNet

Companies & Universities supporting DyNet

Carnegie Mellon University
Bar-Ilan University
Petuum
Allen Institute for Artificial Intelligence
Nara Institute of Science and Technology
University of Washington
Unbabel

About

DyNet is a neural network library developed by Carnegie Mellon University and many others. It is written in C++ (with bindings in Python) and is designed to be efficient when run on either CPU or GPU, and to work well with networks that have dynamic structures that change for every training instance. For example, these kinds of networks are particularly important in natural language processing tasks, and DyNet has been used to build state-of-the-art systems for syntactic parsing, machine translation, morphological inflection, and many other application areas.

Check out the tech report

News