Tập hợp Deep Learning code
Tập hợp Deep
Learning code để cùng nghiên cứu nha các bạn, các code chủ yếu là matlab, C++,
Python, nếu tìm được những code mới , mình sẽ đưa lên sau, và nếu các bạn có những
link code khác, nếu được thì cung cấp để cùng nghiên cứu nhé !!!
-----------------------------------------------------------------------------------------------------
Theano
code
from: http://deeplearning.net/
Deep Learning
Tutorial notes and code
code from:
lisa-lab
A Matlab
toolbox for Deep Learning
code from:
RasmusBerg Palm
deepmat
Matlab Code
for Restricted/Deep BoltzmannMachines and Autoencoder
code from:
KyungHyun Cho http://users.ics.aalto.fi/kcho/
Training a
deep autoencoder or a classifieron MNIST digits
code from:
Ruslan Salakhutdinov and GeoffHinton
CNN -
Convolutional neural network class
Code
from: matlab
Neural Network
for Recognition ofHandwritten Digits (CNN)
cuda-convnet
A fast
C++/CUDA implementation ofconvolutional neural networks
matrbm
a small
library that can train RestrictedBoltzmann Machines, and also Deep Belief
Networks of stacked RBM's.
code from:
Andrej Karpathy
Exercise
from UFLDL Tutorial:
and
tornadomeet’s bolg: http://www.cnblogs.com/tornadomeet/tag/Deep%20Learning/
Conditional
Restricted Boltzmann Machines
from Graham
Taylor http://www.cs.nyu.edu/~gwtaylor/
Factored
Conditional Restricted BoltzmannMachines
from Graham
Taylor http://www.cs.nyu.edu/~gwtaylor/
Marginalized
Stacked Denoising Autoencodersfor Domain Adaptation
Tiled
Convolutional Neural Networks
tiny-cnn:
A C++11
implementation of convolutionalneural networks
myCNN
Adaptive
Deconvolutional Network Toolbox
convolutionalRBM.m
A MATLAB / MEX
/ CUDA-MEX implementation ofConvolutional Restricted Boltzmann Machines.
rbm-mnist
C++ 11
implementation of Geoff Hinton'sDeep Learning matlab code
Learning Deep
Boltzmann Machines
Code provided
by Ruslan Salakhutdinov
Efficient
sparse coding algorithms
Linear Spatial
Pyramid Matching UsingSparse Coding for Image Classification
SPAMS
(SPArse
Modeling Software) is anoptimization toolbox for solving various sparse
estimation problems.
sparsenet
Sparse coding
simulation software
fast dropout
training
Deep Learning
of Invariant Features viaSimulated Fixations in Video
Sparse
filtering
k-means
others:
1. Theano –
CPU/GPU symbolic expression compiler in python (from MILA lab at University of
Montreal)
2. Torch – provides a Matlab-like environment for
state-of-the-art machine learning algorithms in lua (from Ronan Collobert,
Clement Farabet and Koray Kavukcuoglu)
3. Pylearn2 -
Pylearn2 is a library designed to make machine learning research easy.
4. Blocks -
A Theano framework for training neural networks
5. Caffe -Caffe
is a deep learning framework made with expression, speed, and modularity in
mind.Caffe is a deep learning framework made with expression, speed, and
modularity in mind.
6. Lasagne -
Lasagne is a lightweight library to build and train neural networks in Theano.
7. Keras- A theano based deep learning library.
8. Deep Learning
Tutorials – examples of how to do Deep Learning with Theano (from
LISA lab at University of Montreal)
9. DeepLearnToolbox – A Matlab toolbox for Deep Learning
(from Rasmus Berg Palm)
10. 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.
11. Deep Belief Networks. Matlab code for learning Deep Belief
Networks (from Ruslan Salakhutdinov).
12. RNNLM-
Tomas Mikolov’s Recurrent Neural Network based Language models Toolkit.
13. RNNLIB-RNNLIB
is a recurrent neural network library for sequence learning problems.
Applicable to most types of spatiotemporal data, it has proven particularly
effective for speech and handwriting recognition.
14. matrbm.
Simplified version of Ruslan Salakhutdinov’s code, by Andrej Karpathy (Matlab).
15. deepmat-
Deepmat, Matlab based deep learning algorithms.
16. Estimating Partition Functions of RBM’s. Matlab code for
estimating partition functions of Restricted Boltzmann Machines using Annealed
Importance Sampling (from Ruslan Salakhutdinov).
17. Learning Deep
Boltzmann Machines Matlab code for training and fine-tuning
Deep Boltzmann Machines (from Ruslan Salakhutdinov).
18. The LUSH programming
language and development environment, which is used @ NYU for deep
convolutional networks
19. 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.
20. MShadow - MShadow is a lightweight CPU/GPU
Matrix/Tensor Template Library in C++/CUDA. The goal of mshadow is to support
efficient, device invariant and simple tensor library for machine learning
project that aims for both simplicity and performance. Supports CPU/GPU/Multi-GPU
and distributed system.
21. CXXNET - CXXNET is fast, concise, distributed
deep learning framework based on MShadow. It is a lightweight and easy
extensible C++/CUDA neural network toolkit with friendly Python/Matlab
interface for training and prediction.
22. Nengo-Nengo is a graphical and scripting based software
package for simulating large-scale neural systems.
23. 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 byPierre Sermanet at NYU.
24. cudamat is
a GPU-based matrix library for Python. Example code for training Neural
Networks and Restricted Boltzmann Machines is included.
25. 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.
26. 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).
27. 3-way factored RBM and mcRBM is python code calling CUDAMat to train models
of natural images (from Marc’Aurelio Ranzato).
28. Matlab code for training conditional RBMs/DBNs and factored conditional RBMs (from Graham Taylor).
29. mPoT is python code using CUDAMat and gnumpy to train
models of natural images (from Marc’Aurelio Ranzato).
30. neuralnetworks is a java based gpu library for deep
learning algorithms.
31. ConvNet is
a matlab based convolutional neural network toolbox.
32.
Comments
Post a Comment