Torch
Torch is a machine learning library and scientific computing framework for LuaJIT
Features
Torch is a scientific computing framework with support for machine learning algorithms. It provides N-dimensional arrays, with support for routines for indexing, slicing, transposing, etc.
Torch puts GPU first. It has an interface to C via LuaJIT, linear algebra & numeric optimization routines, neural network and energy-based models. It is embeddable, with ports to iOS and Android backends.
System Requirements
- Version ↓
| # | Recommended |
|---|---|
| 1 | NVIDIA® CUDA® 7.5 or newer (For Pascal GPUs, CUDA 8.0 or newer) |
| 2 | cuDNN v5.0 or newer |
| 3 | Ubuntu 14.x or newer (or any 64-bit Linux if you choose to build from source) |
Ratings
Not available, but we appreciate help! You can help us improve this page.
Developer
Ronan Collobert(OD), Koray Kavukcuoglu(OD), Clement Farabet(OD), Soumith Chintala, Other contributors
Written in
Lua, C, LuaJIT, CUDA, C++
Initial Release
October 2002
Repository
License
BSD-3
Categories
Alternatives
Machine Learning
OpenCV
Apache Mahout
Apache MXNet (Incubating)
Apache Spark
Apache SystemML
Eclipse Deeplearning4j
MALLET
Massive Online Analysis (MOA)
mlpack
Orange
PyTorch
scikit-learn
TensorFlow
The Microsoft Cognitive Toolkit
Weka
Yooreeka
Deep Learning
OpenNN
Apache MXNet (Incubating)
Apache SystemML
Caffe
Eclipse Deeplearning4j
PyTorch
TensorFlow
The Microsoft Cognitive Toolkit
Weka
Notes
This page was last updated with commit: Following: - Fixed: missing sources for features now added - Removed: Google Analytics Async (deprecated) - Added: missing aria-labels to input elements - Updated: partials/seo.html code for new data structure - Fixed: changed aria-label to title for span and divs - Fixed: color of status icon on softpages not appearing correctly (5221a6e)