Talk:Comparison of deep learning software/Resources: Difference between revisions

Revision as of 13:04, 29 September 2016

Latest revision as of 01:55, 10 March 2018

(31 intermediate revisions by 15 users not shown)

Line 1:

{{Underlinked|date=March 2016}}

This page lists resources that can be useful to the [[Comparison of deep learning software]] page.

==Deep learning software not yet covered==

* [https://github.com/dritchie/adnn adnn] – Javascript neural networks

* [https://github.com/mila-udem/blocks Blocks] – Theano framework for building and training neural networks

This is a list of deep learning software that is not listed on the [[Comparison of deep learning software|main page]] because they lack a Wikipedia article. If you would like to see any of these pieces of software listed there, you are welcome to create a Wikipedia article for it.

* [https://github.com/yahoo/CaffeOnSpark CaffeOnSpark] – Scalable deep learning package running Caffe on [[Apache Spark|Spark]] and [[Apache Hadoop|Hadoop]] clusters with [[peer-to-peer]] communication

* [http://arxiv.org/abs/1606.06234 CNNLab] – Deep learning framework using GPU and FPGA-based accelerators

* [[adnn]][https://github.com/dritchie/adnn adnn] – Javascript neural networks

* [http://cs.stanford.edu/people/karpathy/convnetjs/ ConvNetJS] – Javascript library for training deep learning models entirely in a web browser

* Blocks[https://github.com/rdevonmila-udem/cortex Cortexblocks] – Theano-based deepframework learningfor toolboxbuilding forand training neural neuroimagingnetworks

* [[Caffe2]][https://caffe2.ai/] – Deep learning framework built on [[Caffe (software)|Caffe]], developed by [[Facebook]] in cooperation with [[NVIDIA]], [[Qualcomm]], [[Intel]], [[Amazon.com|Amazon]], and [[Microsoft]]<ref>https://caffe2.ai/blog/2017/04/18/caffe2-open-source-announcement.html</ref>

* [https://developer.nvidia.com/cudnn cuDNN] – Highly optimized deep learning computation primitives implemented in CUDA

* [[CaffeOnSpark]][https://github.com/yahoo/CaffeOnSpark CaffeOnSpark] – Scalable deep learning package running Caffe on [[Apache Spark|Spark]] and [[Apache Hadoop|Hadoop]] clusters with [[peer-to-peer]] communication

* [https://sourceforge.net/projects/currennt/ CURRENNT] – CUDA-accelerated toolkit for deep Long Short-Term Memory (LSTM) RNN architectures supporting large data sets not fitting into main memory.

* [[Chainer]][https://chainer.org/] – Flexible neural network framework, adopting a "Define-by-run" scheme where the actual forward computation defines the network

* [https://github.com/hughperkins/DeepCL DeepCL] – OpenCL library to train deep convolutional networks, with APIs for C++, Python and the command line

* [http[CNNLab]][https://deeplearningkitarxiv.org/ DeepLearningKitabs/1606.06234] – Open source deepDeep learning framework forusing iOS,GPU OSand XFPGA-based and tvOS<ref>http://arxiv.org/pdf/1605.04614v1.pdf</ref>accelerators

* [[ConvNetJS]][http://cs.stanford.edu/people/karpathy/convnetjs/ ConvNetJS] – Javascript library for training deep learning models entirely in a web browser

* [https://github.com/rasmusbergpalm/DeepLearnToolbox DeepLearnToolbox] – Matlab/Octave toolbox for deep learning (deprecated)

* [[List of neuroimaging software|Cortex]] – Theano-based deep learning toolbox for neuroimaging

* [http://niclane.org/pubs/deepx_ipsn.pdf DeepX] – Software accelerator for deep learning execution aimed towards mobile devices

* [[cuDNN]][https://developer.nvidia.com/cudnn cuDNN] – Highly optimizedOptimized deep learning computation primitives implemented in CUDA

* [https://github.com/amznlabs/amazon-dsstne DSSTNE] (Deep Scalable Sparse Tensor Network Engine) – [[Amazon.com|Amazon]] developed library for building deep learning models

* [[CURRENNT]][https://sourceforge.net/projects/currennt/ CURRENNT] – CUDA-accelerated toolkit for deep Long Short-Term Memory (LSTM) RNN architectures supporting large data sets not fitting into main memory.

* [https://github.com/yandex/faster-rnnlm Faster RNNLM (HS/NCE) toolkit] – An rnnlm implementation for training on huge datasets and very large vocabularies and usage in real-world ASR and MT problems

* [[Darknet]][https://pjreddie.com/darknet/] - Darknet is an open source neural network framework written in C and CUDA, and supports CPU and GPU computation.

* [https://www.gnu.org/software/gneuralnetwork/ GNU Gneural Network] – GNU package which implements a programmable neural network

* [[DeepCL]][https://github.com/hughperkins/DeepCL DeepCL] – OpenCL library to train deep convolutional networks, with APIs for C++, Python and the command line

* [https://github.com/01org/idlf IDLF] – [[Intel]]® Deep Learning Framework; supports OpenCL (deprecated)

* [http[deeplearn.js]][https://keraspair-code.github.io/ Kerasdeeplearnjs/] – DeepHardware-accelerated deep Learninglearning library for Theanothe andweb TensorFlowbrowser

* [[DeepLearningKit]][http://deeplearningkit.org/] – Open source deep learning framework for iOS, OS X and tvOS<ref>https://arxiv.org/pdf/1605.04614v1.pdf</ref>

* [http://lasagne.readthedocs.org/en/latest/ Lasagne] – Lightweight library to build and train neural networks in Theano

* [[DeepLearnToolbox]][https://github.com/rasmusbergpalm/DeepLearnToolbox DeepLearnToolbox] – Matlab/Octave toolbox for deep learning (deprecated)

* [https://github.com/autumnai/leaf Leaf] – "The Hacker's Machine Learning Engine"; supports OpenCL (official development suspended<ref>{{cite web|author=Michael Hirn|url=https://medium.com/@mjhirn/tensorflow-wins-89b78b29aafb#.u5yveb1le|title=Tensorflow wins|date=9 May 2016|accessdate=17 August 2016|quote=... I will suspend the development of Leaf and focus on new ventures.}}</ref>)

* [[DeepX]][http://arxivniclane.org/abspubs/1605deepx_ipsn.02766 LightNetpdf] – MATLAB-basedSoftware environment accelerator for deep learning execution aimed towards mobile devices

* [[deepy]][https://github.com/zomux/deepy] – Extensible deep learning framework based on Theano

* [http://www.vlfeat.org/matconvnet/ MatConvNet] – CNNs for MATLAB

* [[DSSTNE]][https://github.com/amznlabs/amazon-dsstne DSSTNE] (Deep Scalable Sparse Tensor Network Engine) – [[Amazon.com|Amazon]] developed library for building deep learning models

* [https://github.com/abhinavvishnu/matex MaTEx] – Distributed TensorFlow with MPI by [[PNNL]]

* [[Faster RNNLM (HS/NCE) toolkit]][https://github.com/yandex/faster-rnnlm Faster RNNLM (HS/NCE) toolkit] – An rnnlm implementation for training on huge datasets and very large vocabularies and usage in real-world ASR and MT problems

* [https://github.com/NervanaSystems/neon neon] – Nervana's Python based Deep Learning framework

* [[GNU Gneural Network]][https://www.gnu.org/software/gneuralnetwork/ GNU Gneural Network] – GNU package which implements a programmable neural network

* [http://fr.mathworks.com/products/neural-network/ Neural Network Toolbox] – MATLAB toolbox for neural network creation, training and simulation

* [[IDLF]][https://github.com/baidu01org/paddle PaddlePaddleidlf] – "PArallel Distributed[[Intel]]® Deep LEarning",Learning deepFramework; learningsupports platformOpenCL by [[Baidu]](deprecated)

* Intel [[Math Kernel Library]] (Intel MKL),<ref>https://software.intel.com/en-us/articles/introducing-dnn-primitives-in-intelr-mkl</ref> library of optimized math routines, including optimized deep learning computation primitives

* [https://github.com/purine/purine2 Purine] – Bi-graph based deep learning framework<ref>https://arxiv.org/abs/1412.6249</ref>

* Lasagne[http://deeplearninglasagne.netreadthedocs.org/softwareen/pylearn2latest/ Pylearn2] – Machine learningLightweight library mainlyto build and builttrain onneural topnetworks ofin Theano

* Leaf[https://github.com/autumnai/leaf Leaf] – "The Hacker's Machine Learning Engine"; supports OpenCL (official development suspended<ref>{{cite web|author=Michael Hirn|url=https://medium.com/@mjhirn/tensorflow-wins-89b78b29aafb#.u5yveb1le|title=Tensorflow wins|date=9 May 2016|accessdate=17 August 2016|quote=... I will suspend the development of Leaf and focus on new ventures.}}</ref>)

* [https://scikit-neuralnetwork.readthedocs.org/ scikit-neuralnetwork] – Multi-layer perceptrons as a wrapper for Pylearn2

* [[LightNet]][https://arxiv.org/abs/1605.02766] – MATLAB-based environment for deep learning

* [https://github.com/cgarciae/tensorbuilder Tensor Builder] – Lightweight extensible library for easy creation of deep neural networks using functions from "any Tensor-based library" (requires TensorFlow) through an API based on the Builder Pattern

* [[MaTEx]][https://github.com/hycisabhinavvishnu/TensorGraph TensorGraphmatex] – FrameworkDistributed forTensorFlow buildingwith anyMPI modelsby based on TensorFlow[[PNNL]]

* Mocha[https://github.com/pluskid/Mocha.jl] – Deep learning framework for [[Julia (programming language)|Julia]], inspired by Caffe

* [https://research.googleblog.com/2016/08/tf-slim-high-level-library-to-define.html TF-Slim] – High level library to define complex models in TensorFlow

* neon[https://github.com/Ivaylo-PopovNervanaSystems/Theano-Lights Theano-Lightsneon] – DeepNervana's learningPython researchbased frameworkDeep basedLearning on Theanoframework

* Purine[https://github.com/nyanppurine/tiny-dnn tiny-dnnpurine2] – Header only, dependencyBi-freegraph based deep learning framework in C++11<ref>https://arxiv.org/abs/1412.6249</ref>

* [[Pylearn2]][http://deeplearning.net/software/pylearn2/] – Machine learning library mainly built on top of Theano

* [https://github.com/torchnet/torchnet torchnet] – Torch framework providing a set of abstractions aiming at encouraging code re-use as well as encouraging modular programming<ref>https://code.facebook.com/posts/580706092103929</ref><ref>{{cite web|author1=Ronan Collobert|author2=Laurens van der Maaten|author3=Armand Joulin|title=Torchnet: An Open-Source Platform for (Deep) Learning Research|url=https://lvdmaaten.github.io/publications/papers/Torchnet_2016.pdf|publisher=Facebook AI Research|accessdate=24 June 2016}}</ref>

* [[scikit-neuralnetwork]][https://scikit-neuralnetwork.readthedocs.org/ scikit-neuralnetwork] – Multi-layer perceptrons as a wrapper for Pylearn2

* [https://github.com/Samsung/veles Veles] – Distributed machine learning platform by [[Samsung]]

* [[sklearn-theano]][https://github.com/sklearn-theano/sklearn-theano] – Scikit-learn compatible tools using theano

* [[Tensor Builder]][https://github.com/cgarciae/tensorbuilder Tensor Builder] – Lightweight extensible library for easy creation of deep neural networks using functions from "any Tensor-based library" (requires TensorFlow) through an API based on the Builder Pattern

* [[TensorGraph]][https://github.com/hycis/TensorGraph] – Framework for building any models based on TensorFlow

* [[TensorFire]][https://tenso.rs/] – Neural networks framework for the web browser, accelerated by WebGL

* [[TF Learn (Scikit Flow)]][https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/learn/python/learn] – Simplified interface for TensorFlow

* [[TF-Slim]][https://research.googleblog.com/2016/08/tf-slim-high-level-library-to-define.html TF-Slim] – High level library to define complex models in TensorFlow

* [[TFLearn]][http://tflearn.org/] – Deep learning library featuring a higher-level API for TensorFlow

* [[Theano-Lights]][https://github.com/Ivaylo-Popov/Theano-Lights] – Deep learning research framework based on Theano

* [[tiny-dnn]][https://github.com/nyanp/tiny-dnn] – Header only, dependency-free deep learning framework in C++11

* [[torchnet]][https://github.com/torchnet/torchnet torchnet] – Torch framework providing a set of abstractions aiming at encouraging code re-use as well as encouraging modular programming<ref>https://code.facebook.com/posts/580706092103929</ref><ref>{{cite web|author1=Ronan Collobert|author2=Laurens van der Maaten|author3=Armand Joulin|title=Torchnet: An Open-Source Platform for (Deep) Learning Research|url=https://lvdmaaten.github.io/publications/papers/Torchnet_2016.pdf|publisher=Facebook AI Research|accessdate=24 June 2016}}</ref>

* Veles[https://github.com/abhinavvishnuSamsung/matex MaTExveles] – Distributed TensorFlowmachine withlearning MPIplatform by [[PNNLSamsung]]

==Related software==

* [[Deep Visualization Toolbox]][https://github.com/yosinski/deep-visualization-toolbox Deep Visualization Toolbox]<ref>httphttps://arxiv.org/abs/1506.06579</ref><ref>http://yosinski.com/deepvis</ref> – Software tool for "probing" DNNs by feeding them image data and watching the reaction of every neuron, and for visualizing what a specific neuron "wants to see the most"

* [[LSTMVis]][http://lstm.seas.harvard.edu/ LSTMVis] – A visual analysis tool for recurrent neural networks

* [[pastalog]][https://github.com/rewonc/pastalog pastalog] – Simple, realtime visualization of neural network training performance

==References==

Line 58 ⟶ 67:

* [https://github.com/zer0n/deepframeworks/blob/master/README.md Evaluation of Deep Learning Toolkits], an evaluation of Caffe, CNTK, TensorFlow, Theano, and Torch with ratings on different aspects

* [https://www.youtube.com/watch?v=Vf_-OkqbwPo YouTube: CS231n Winter 2016: Lecture 12: Deep Learning libraries] – A comparison of Caffe, Torch, Theano and Tensorflow

* [http://blog.apcelent.com/most-popular-deep-learning-library-2015.html?utm_source=fb.com&utm_medium=marketing&utm_campaign=blog 10 Most Popular Deep Learning Libraries Started in 2015]

* [http://www.infoworld.com/article/3026262/data-science/13-framewoks-for-mastering-machine-learning.html 13 frameworks for mastering machine learning]

* [httphttps://venturebeat.com/2015/11/14/deep-learning-frameworks/ Want an open-source deep learning framework? Take your pick]

* [https://www.quora.com/What-is-the-best-deep-learning-library-at-the-current-stage-for-working-on-large-data What is the best deep learning library at the current stage for working on large data?]

* [https://github.com/josephmisiti/awesome-machine-learning Awesome Machine Learning] – A large list of machine learning frameworks, libraries and software by language

Line 66 ⟶ 75:

* [https://esciencegroup.com/2016/02/08/tensorflow-meets-microsofts-cntk/ TensorFlow Meets Microsoft’s CNTK] – Comparison of [[TensorFlow]] and [[CNTK]]

* [https://developer.nvidia.com/deep-learning-frameworks Deep Learning Frameworks] – Short list of deep learning frameworks recommended by [[Nvidia]]

* [https://github.com/jtoy/awesome-tensorflow#libraries Awesome TensorFlow – Libraries]

* [http://deep-learning.sg.tn/index.php/2-non-categorise/5-popular-deep-learning-libraries Popular Deep Learning Libraries]

{{DEFAULTSORT:Comparison of deep learning software Resources}}

[[Category:Data mining and machine learning software]]