Jump to content

Talk:Comparison of deep learning software/Resources

Page contents not supported in other languages.
From Wikipedia, the free encyclopedia
< Talk:Comparison of deep learning software
This is the current revision of this page, as edited by Huon (talk | contribs) at 01:55, 10 March 2018 (uncategorize). The present address (URL) is a permanent link to this version.
(diff) ← Previous revision | Latest revision (diff) | Newer revision → (diff)

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

Deep learning software not yet covered

[edit]

This is a list of deep learning software that is not listed on the 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.

  • adnn[1] – Javascript neural networks
  • Blocks[2] – Theano framework for building and training neural networks
  • Caffe2[3] – Deep learning framework built on Caffe, developed by Facebook in cooperation with NVIDIA, Qualcomm, Intel, Amazon, and Microsoft[1]
  • CaffeOnSpark[4] – Scalable deep learning package running Caffe on Spark and Hadoop clusters with peer-to-peer communication
  • Chainer[5] – Flexible neural network framework, adopting a "Define-by-run" scheme where the actual forward computation defines the network
  • CNNLab[6] – Deep learning framework using GPU and FPGA-based accelerators
  • ConvNetJS[7] – Javascript library for training deep learning models entirely in a web browser
  • Cortex – Theano-based deep learning toolbox for neuroimaging
  • cuDNN[8] – Optimized deep learning computation primitives implemented in CUDA
  • CURRENNT[9] – CUDA-accelerated toolkit for deep Long Short-Term Memory (LSTM) RNN architectures supporting large data sets not fitting into main memory.
  • Darknet[10] - Darknet is an open source neural network framework written in C and CUDA, and supports CPU and GPU computation.
  • DeepCL[11] – OpenCL library to train deep convolutional networks, with APIs for C++, Python and the command line
  • deeplearn.js[12] – Hardware-accelerated deep learning library for the web browser
  • DeepLearningKit[13] – Open source deep learning framework for iOS, OS X and tvOS[2]
  • DeepLearnToolbox[14] – Matlab/Octave toolbox for deep learning (deprecated)
  • DeepX[15] – Software accelerator for deep learning execution aimed towards mobile devices
  • deepy[16] – Extensible deep learning framework based on Theano
  • DSSTNE[17] (Deep Scalable Sparse Tensor Network Engine) – Amazon developed library for building deep learning models
  • Faster RNNLM (HS/NCE) toolkit[18] – An rnnlm implementation for training on huge datasets and very large vocabularies and usage in real-world ASR and MT problems
  • GNU Gneural Network[19] – GNU package which implements a programmable neural network
  • IDLF[20] – Intel® Deep Learning Framework; supports OpenCL (deprecated)
  • Intel Math Kernel Library (Intel MKL),[3] library of optimized math routines, including optimized deep learning computation primitives
  • Lasagne[21] – Lightweight library to build and train neural networks in Theano
  • Leaf[22] – "The Hacker's Machine Learning Engine"; supports OpenCL (official development suspended[4])
  • LightNet[23] – MATLAB-based environment for deep learning
  • MaTEx[24] – Distributed TensorFlow with MPI by PNNL
  • Mocha[25] – Deep learning framework for Julia, inspired by Caffe
  • neon[26] – Nervana's Python based Deep Learning framework
  • Purine[27] – Bi-graph based deep learning framework[5]
  • Pylearn2[28] – Machine learning library mainly built on top of Theano
  • scikit-neuralnetwork[29] – Multi-layer perceptrons as a wrapper for Pylearn2
  • sklearn-theano[30] – Scikit-learn compatible tools using theano
  • Tensor Builder[31] – 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[32] – Framework for building any models based on TensorFlow
  • TensorFire[33] – Neural networks framework for the web browser, accelerated by WebGL
  • TF Learn (Scikit Flow)[34] – Simplified interface for TensorFlow
  • TF-Slim[35] – High level library to define complex models in TensorFlow
  • TFLearn[36] – Deep learning library featuring a higher-level API for TensorFlow
  • Theano-Lights[37] – Deep learning research framework based on Theano
  • tiny-dnn[38] – Header only, dependency-free deep learning framework in C++11
  • torchnet[39] – Torch framework providing a set of abstractions aiming at encouraging code re-use as well as encouraging modular programming[6][7]
  • Veles[40] – Distributed machine learning platform by Samsung
[edit]
  • Deep Visualization Toolbox[41][8][9] – 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[42] – A visual analysis tool for recurrent neural networks
  • pastalog[43] – Simple, realtime visualization of neural network training performance

References

[edit]
  1. ^ https://caffe2.ai/blog/2017/04/18/caffe2-open-source-announcement.html
  2. ^ https://arxiv.org/pdf/1605.04614v1.pdf
  3. ^ https://software.intel.com/en-us/articles/introducing-dnn-primitives-in-intelr-mkl
  4. ^ Michael Hirn (9 May 2016). "Tensorflow wins". Retrieved 17 August 2016. ... I will suspend the development of Leaf and focus on new ventures.
  5. ^ https://arxiv.org/abs/1412.6249
  6. ^ https://code.facebook.com/posts/580706092103929
  7. ^ Ronan Collobert; Laurens van der Maaten; Armand Joulin. "Torchnet: An Open-Source Platform for (Deep) Learning Research" (PDF). Facebook AI Research. Retrieved 24 June 2016.
  8. ^ https://arxiv.org/abs/1506.06579
  9. ^ http://yosinski.com/deepvis
[edit]
Retrieved from "https://en.wikipedia.org/w/index.php?title=Talk:Comparison_of_deep_learning_software/Resources&oldid=829672521"