Torch7: A Matlab-like Environment for Machine Learning

TLDR

Torch7 is a versatile numeric computing framework and machine learning library that extends Lua. Torch7 aims to provide a flexible environment for designing and training learning machines. Torch7 achieves flexibility through Lua scripting and high performance via efficient OpenMP/SSE and CUDA implementations, while enabling easy interfacing with third‑party software.

Abstract

Torch7 is a versatile numeric computing framework and machine learning library that extends Lua. Its goal is to provide a flexible environment to design and train learning machines. Flexibility is obtained via Lua, an extremely lightweight scripting language. High performance is obtained via efficient OpenMP/SSE and CUDA implementations of low-level numeric routines. Torch7 can easily be interfaced to third-party software thanks to Lua’s light interface.