clab/dynet
A C++ neural network library with Python bindings developed by Carnegie Mellon University for efficient training on CPU and GPU.
Not currently ranked — collecting fresh signals.
star history
DyNet is a neural network library designed for networks with dynamic structures that change per training instance. It is written in C++ with Python bindings and optimized for both CPU and GPU execution. The library has been widely used in natural language processing applications including syntactic parsing, machine translation, and morphological inflection.
Frequently asked
- What is clab/dynet?
- A C++ neural network library with Python bindings developed by Carnegie Mellon University for efficient training on CPU and GPU.
- Is dynet open source?
- Yes — clab/dynet is open source, released under the Apache-2.0 license.
- What language is dynet written in?
- clab/dynet is primarily written in C++.
- How popular is dynet?
- clab/dynet has 3.4k stars on GitHub.
- Where can I find dynet?
- clab/dynet is on GitHub at https://github.com/clab/dynet.