Бесплатные программы для глубинного обучения

Фреймворки, библиотеки программ и отдельные программы для глубинного обучения.

Apache SINGA

BigDL

Caffe

Deeplearning4j

Dlib

Keras

MatConvNet

Microsoft Cognitive Toolkit

MXNet

OpenNN

TensorFlow

Theano

Torch

И ещё несколько вариантов (часть из них могут быть платными):

 

  • adnn – Javascript neural networks
  • Blocks – Theano framework for building and training neural networks
  • Caffe2 – Deep learning framework built on Caffe, developed by Facebook in cooperation with NVIDIA, Qualcomm, Intel, Amazon, and Microsoft
  • CaffeOnSpark – Scalable deep learning package running Caffe on Spark and Hadoop clusters with peer-to-peer communication
  • CNNLab – Deep learning framework using GPU and FPGA-based accelerators
  • ConvNetJS – Javascript library for training deep learning models entirely in a web browser
  • Cortex – Theano-based deep learning toolbox for neuroimaging
  • cuDNN – Optimized deep learning computation primitives implemented in CUDA
  • CURRENNT – CUDA-accelerated toolkit for deep Long Short-Term Memory (LSTM) RNN architectures supporting large data sets not fitting into main memory.
  • DeepCL – OpenCL library to train deep convolutional networks, with APIs for C++, Python and the command line
  • deeplearn.js – Hardware-accelerated deep learning library for the web browser
  • DeepLearningKit – Open source deep learning framework for iOS, OS X and tvOS
  • DeepLearnToolbox – Matlab/Octave toolbox for deep learning (deprecated)
  • DeepX – Software accelerator for deep learning execution aimed towards mobile devices
  • deepy – Extensible deep learning framework based on Theano
  • DSSTNE (Deep Scalable Sparse Tensor Network Engine) – Amazon developed library for building deep learning models
  • 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
  • GNU Gneural Network – GNU package which implements a programmable neural network
  • IDLF – Intel® Deep Learning Framework; supports OpenCL (deprecated)
  • Intel Math Kernel Library (Intel MKL), library of optimized math routines, including optimized deep learning computation primitives
  • Keras – Deep Learning library for Theano and TensorFlow
  • Lasagne – Lightweight library to build and train neural networks in Theano
  • Leaf – «The Hacker’s Machine Learning Engine»; supports OpenCL (official development suspended[4])
  • LightNet – MATLAB-based environment for deep learning
  • MatConvNet – CNNs for MATLAB
  • MaTEx – Distributed TensorFlow with MPI by PNNL
  • Mocha – Deep learning framework for Julia, inspired by Caffe
  • neon – Nervana’s Python based Deep Learning framework
  • Neural Network Toolbox – MATLAB toolbox for neural network creation, training and simulation
  • PaddlePaddle – «PArallel Distributed Deep LEarning», deep learning platform
  • Purine – Bi-graph based deep learning framework
  • Pylearn2 – Machine learning library mainly built on top of Theano
  • Pytorch — Python based implementation of Torch API, allows for dynamic graph construction
  • scikit-neuralnetwork – Multi-layer perceptrons as a wrapper for Pylearn2
  • sklearn-theano – Scikit-learn compatible tools using theano
  • 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 – Framework for building any models based on TensorFlow
  • TensorFire – Neural networks framework for the web browser, accelerated by WebGL
  • TF Learn (Scikit Flow) – Simplified interface for TensorFlow
  • TF-Slim – High level library to define complex models in TensorFlow
  • TFLearn – Deep learning library featuring a higher-level API for TensorFlow
  • Theano-Lights – Deep learning research framework based on Theano
  • tiny-dnn – Header only, dependency-free deep learning framework in C++11
  • torchnet – Torch framework providing a set of abstractions aiming at encouraging code re-use as well as encouraging modular programming
  • Veles – Distributed machine learning platform by Samsung

 
Источник

Data Scientist # 1

Машинное обучение, большие данные, наука о данных, анализ данных, цифровой маркетинг, искусственный интеллект, нейронные сети, глубокое обучение, data science, data scientist, machine learning, artificial intelligence, big data, deep learning

Данные — новый актив!

Эффективно управлять можно только тем, что можно измерить.
Copyright © 2020 Data Scientist. Все права защищены.