Torch is a scientific computing framework with broad support for machine learning algorithms that puts GPUs first. Easy and fast scripting language is easy and efficient to use thanks to LuaJIT and an underlying C/CUDA application.
- A powerful N-dimensional array
- indexing, slicing, transfer support
- Incredible interface support to C via LuaJIT
- Linear algebra routines
- Neural network and energy-based models
- Digital optimization routines
- Fast and efficient GPU support
- Can be embedded with iOS and Android backend ports
Why Use Torch?
Torch's goal is to achieve maximum flexibility and speed in building your scientific algorithms while making the process extremely simple. Torch comes with a broad ecosystem of community-driven packages in machine learning, computer vision, signal processing, parallel processing, image, video, audio, and networking, and is built on the Lua community.
At the heart of the Torch is the popular neural network and optimization libraries, which are easy to use, while having maximum flexibility in implementing complex neural network topologies. You can create arbitrary graphics of neural networks and make them efficiently parallel on CPUs and GPUs.
Use of Torch
Torch is constantly evolving: it is already used in Facebook, Google, Twitter, NYU, IDIAP, Purdue and many other companies and research laboratories.