Torch is an open source machine learning library, a scientific computational framework and a scripting language. It is built using the Lua programming language and runs on LuaJIT compiler and an underlying C/CUDA implementation. It contains well-developed neural networks and optimization libraries.
It gives maximum flexibility and speed in building scientific algorithms and arbitrary acyclic computation graphs with automatic differentiation functionalities and parallelize them over CPUs and GPUs . It comes with a large ecosystem of community-driven packages in machine learning, computer vision, signal processing, parallel processing, image, video, audio and networking among others.
Main features of Torch framework are as follow:
- N-dimensional array
- different routines for indexing, slicing, transposing
- interface to C via LuaJIT
- linear algebra routines
- neural network and energy-based models
- numeric optimization routines
- fast and efficient GPU support
- embeddable with ports to iOS and Android backends
Comparative Study of Deep Learning Software Frameworks
Soheil Bahrampour, Naveen Ramakrishnan, Lukas Schott and Mohak Shah
Documentaries, videos and podcasts
Practical 1.1 – Torch
10 August 2016