深度学习 deep learning 部分工具箱和源码 code

本文是网络部分资源的整合

Software links

Theano – CPU/GPU symbolic expression compiler in python (from LISA lab at University of Montreal)

Pylearn2 - Pylearn2 is a library designed to make machine learning research easy.

Torch – provides a Matlab-like environment for state-of-the-art machine learning algorithms in lua (from Ronan Collobert, Clement Farabet and Koray Kavukcuoglu)

Deep Learning Tutorials – examples of how to do Deep Learning with Theano (from LISA lab at University of Montreal)

DeepLearnToolbox – A Matlab toolbox for Deep Learning (from Rasmus Berg Palm)

Cuda-Convnet – A fast C++/CUDA implementation of convolutional (or more generally, feed-forward) neural networks. It can model arbitrary layer connectivity and network depth. Any directed acyclic graph of layers will do. Training is done using the back-propagation algorithm.

Deep Belief Networks. Matlab code for learning Deep Belief Networks (from Ruslan Salakhutdinov).

matrbm. Simplified version of Ruslan Salakhutdinov’s code, by Andrej Karpathy (Matlab).

deepmat- Deepmat, Matlab based deep learning algorithms.

Estimating Partition Functions of RBM’s. Matlab code for estimating partition functions of Restricted Boltzmann Machines using Annealed Importance Sampling (from Ruslan Salakhutdinov).

Learning Deep Boltzmann Machines Matlab code for training and fine-tuning Deep Boltzmann Machines (from Ruslan Salakhutdinov).

The LUSH programming language and development environment, which is used @ NYU for deep convolutional networks

Eblearn.lsh is a LUSH-based machine learning library for doing Energy-Based Learning. It includes code for “Predictive Sparse Decomposition” and other sparse auto-encoder methods for unsupervised learning. Koray Kavukcuoglu provides Eblearn code for several deep learning papers on this page.

Eblearn is a C++ machine learning library with a BSD license for energy-based learning, convolutional networks, vision/recognition applications, etc. EBLearn is primarily maintained by Pierre Sermanet at NYU.

cudamat is a GPU-based matrix library for Python. Example code for training Neural Networks and Restricted Boltzmann Machines is included.

Gnumpy is a Python module that interfaces in a way almost identical to numpy, but does its computations on your computer’s GPU. It runs on top of cudamat.

The CUV Library (github link) is a C++ framework with python bindings for easy use of Nvidia CUDA functions on matrices. It contains an RBM implementation, as well as annealed importance sampling code and code to calculate the partition function exactly (from AIS lab at University of Bonn).

3-way factored RBM and mcRBM is python code calling CUDAMat to train models of natural images (from Marc’Aurelio Ranzato).

Matlab code for training conditional RBMs/DBNs and factored conditional RBMs (from Graham Taylor).

mPoT is python code using CUDAMat and gnumpy to train models of natural images (from Marc’Aurelio Ranzato).

If your software belongs here, email us and let us know.

PYTHON：

★★★★★ 五星
Theano – CPU/GPU 符号表示编译器in python (from LISA lab at University of Montreal)  

相关资源：

Deep Learning Tutorials – 使用Theano实现深度学习的示例 (from LISA lab at University of Montreal)

Pylearn2 - Pylearn2是一个机器学习库，功能建立在Theano之上.

Gnumpy 是一个Python模块，提供与numpy相似的接口，使用GPU进行计算，运行于cudamat之上.

cudamat 是一个基于GPU的矩阵库，包括训练Neural Networks and Restricted Boltzmann Machines的示例代码。

3-way factored RBM andmcRBM 是Python代码，调用CUDAMat用于为自然图像训练模型(fromMarc’Aurelio Ranzato).

mPoT 是Python代码，调用CUDAMat和gnumpy用于为自然图像训练模型 (fromMarc’Aurelio Ranzato).

 

MATLAB：

★★★★★五星

DeepLearnToolbox – A Matlab toolbox for Deep Learning (from Rasmus Berg Palm)

Matlab code for training conditional RBMs/DBNs and factored conditional RBMs (from Graham Taylor).

★★★★四星

Deep Belief Networks. Matlab代码用于学习深度信念网络(Deep Belief Networks) (from Ruslan Salakhutdinov).

Estimating Partition Functions of RBM’s. Matlab代码用于使用退火重要性采样(Annealed Importance Sampling)估计Restricted Boltzmann Machines的剖分函数(the partition function)   (from Ruslan Salakhutdinov).

Learning Deep Boltzmann MachinesMatlab代码用于训练与微调Deep Boltzmann Machines (from Ruslan Salakhutdinov).

★★★ 三星

matrbm. Ruslan Salakhutdinov’s代码的简化版本, by Andrej Karpathy (Matlab).

C++：

★★★三星

Cuda-Convnet –一个快速的卷积(或更一般地，前向式feed-forward)神经网络的C++/CUDA实现。可用于建模arbitrary layer connectivity and network depth. Any directed acyclic graph of layers will do. Training is done using the back-propagation algorithm.

★★★★★五星

Eblearn 是 C++机器学习库，BSD许可证，用于基于能量的学习(energy-based learning),卷积网络(convolutional networks), 视觉/识别应用(vision/recognition applications)等。EBLearn最初由Pierre Sermanet at NYU维护。

★★★三星

The CUV Library (github link) 是一个C++库，包括python绑定，易于操作Nvidia CUDA矩阵函数。包括一个RBM实现，退火重要性采样代码( annealed importance sampling)，以及精确计算剖分函数(the partition function)的代码 (fromAIS lab at University of Bonn).

LUSH：

★★两星

Eblearn.lsh 是基于 LUSH的机器学习库，用于实现基于能量的学习(Energy-Based Learning). 它包括 “Predictive Sparse Decomposition” 的代码以及其他非监督学习的sparse auto-encoder methods.Koray Kavukcuoglu在其主页上提供多篇深度学习相关论文的Eblearn代码。

相关资源：

LUSH 编程语言及开发环境, 用于@ NYU 开发深度卷积网络。LUSH全称是Lisp Universal Shell，Wiki上有介绍。

LUA：

★★★★★ 五星

Torch – 提供与Matlab相似的环境，用于最新的机器学习算法。(from Ronan Collobert, Clement Farabet and Koray Kavukcuoglu)