Deepnet
GPU-accelerated Python implementation of six fundamental deep learning algorithms using CUDA libraries.
What is Deepnet?
Deepnet is a Python library that implements six fundamental deep learning algorithms with GPU acceleration using CUDA technology. It provides efficient implementations of neural networks including feed-forward nets, restricted Boltzmann machines, deep belief nets, autoencoders, deep Boltzmann machines, and convolutional neural networks. The library solves the problem of slow training times by leveraging GPU computing for faster neural network experimentation and development.
Machine learning researchers, deep learning practitioners, and developers who need efficient implementations of classic deep learning algorithms with GPU acceleration for experimentation and prototyping.
Developers choose Deepnet for its focused collection of well-implemented core algorithms with built-in GPU acceleration, eliminating the need to write low-level CUDA code while providing significant performance improvements over CPU-based implementations.
Overview
Implementation of some deep learning algorithms.
Use Cases
Best For
- Experimenting with classic deep learning architectures
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.
