Torch logo

Torch

Supports a wide range of machine learning algorithms and leverages GPUs for computations.

Made by Clément Farabet

    What is Torch?

    Torch is a versatile scientific computing framework that prioritizes the utilization of GPU hardware to power a wide range of machine learning algorithms. With its Lua-based scripting language, Torch offers an efficient and user-friendly interface, seamlessly integrating an underlying C/CUDA implementation for optimized performance. This open-source tool, boasting 8.8K GitHub stars and 2.4K forks, has established itself as a prominent player in the Machine Learning Tools ecosystem, providing researchers and developers with a robust platform to tackle complex scientific computing challenges

    Highlights

    • GPU-centric design for accelerated machine learning computations
    • Support for a diverse range of machine learning algorithms and techniques
    • Lua-based scripting language for an intuitive and productive development experience
    • Efficient C/CUDA-based implementation for high-performance computing

    Platforms

    • Web

    Social

    Features

      • Fast and efficient GPU support

      • Embeddable, with ports to iOS and Android backends

      • A powerful N-dimensional array

      • Amazing interface to C, via LuaJIT

      • Lots of routines for indexing, slicing,

      • Linear algebra routines

      • Numeric optimization routines

      • Neural network, and energy-based models