dpnn
A Torch7 package providing extended neural network modules, criterions, and utilities for deep learning research.
What is dpnn?
dpnn is a Torch7 package that extends the core `nn` library with additional neural network modules, criterions, and training utilities. It provides specialized components for computer vision, reinforcement learning, and efficient model training, addressing gaps in the standard library for research and complex architectures.
Deep learning researchers and practitioners using Torch7 who need advanced modules, reinforcement learning tools, or efficiency optimizations beyond the standard `nn` package.
It offers a curated collection of battle-tested extensions from the dp framework, enabling faster experimentation with state-of-the-art techniques like REINFORCE, NCE, and specialized architectures without reinventing the wheel.
Overview
deep extensions to nn
Use Cases
Best For
- Extending Torch7's neural network capabilities with research-oriented modules
- Implementing reinforcement learning models with policy gradient methods
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
