ReadMe
Release Version
beta_1.0
index.py
imageMatlab.py
This is more or less a wrapper for Matplotlib imaging functions such that their behavior is equivalent, in terms of colormap, aspect and so forth, to the expected behavior of Matlab's functions.
sepVocal.py
This script can be used to execute the desired separation. See below for an example of use of this file.
SIMM.py
This script implements the actual algorithm for parameter estimation. It is mainly used by sepVocal.py.
tracking.py
The Viterbi decoding algorithm is implemented in this script.
Requirements:
These scripts have been tested with Python 2.7,
The packages that are required to run the scripts are pydub,ffmepg, Numpy, Spicy, Matplotlib. One can respectively find the latest versions at the following addresses:
http://pydub.com/
https://ffmpeg.org
http://numpy.org/
http://scipy.org/
http://matplotlib.sourceforge.net/
Notes:
Prefer recent versions of the above packages, in order to avoid compatibility issues, notably for Matplotlib. Note that this latter package is not necessary for the program to run, although you might want to watch a bit what is happening!
Spicy should be version 0.8+, since we use its io.wavefile module to read the wave files. We once used the audio lab module, but it would seem that it is a bit more complicated to install (with the benefit that many more file formats are allowed).
Usage:
The easy way to use these scripts is to run the exec package of our release version: http://www.github.com/beata_1.0
for more develop: you can run the index.py on pycharm directly.
note: the output files will create under you source wav file.
ContactMe
Email:xlzhang14@fudan.edu.cn
Auto Speaker Recognition
main.py
the main file for test
audio_record.py
record audio from micro phone
count_days.py
count days between two date. 20110805 20160903
mfcc_feature.py
extract mfcc feature from wav files
SGD.model*
the trained model on train set , and the accurate is 70%
util.py
contains the most useful functions
train
train data is 75% of all the data
test
test data is 25% of all the data and has no overlap with train set
classification_SGD.py
is the main classification function py file , and it used the sklearn's SGD
niter was set 10000 could get 70% of accurate.
classification_BNB.py
this is the sklern naive_bayes BernoulliNB , and it reach to just 56%
classification_DT.py
this is the sklern tree.DecisionTreeClassifier , and it reach to just 63%
classification_GB.py
this is the sklern GradientBoostingClassifier, and it reach to the best now of 76% when n_estimators=1000, but it produce too many model components to store.
classification_GNB.py
this is the sklern naive_bayes GaussianNB, and it reach to just 63%
vote_result.py
add a vote decsion , every method have the acurrcy number ticiks to vote the final answer. after the vote , we achived 96% at test set.
beta1.0
August 26, 2015
IEEEtran is a LaTeX class for authors of the Institute of Electrical and
Electronics Engineers (IEEE) transactions journals and conferences.
This is a small library that can train Restricted Boltzmann Machines, and also Deep Belief Networks of stacked RBM's.
Train RBM's:
%train an RBM with binary visible units and 500 binary hidden
model= rbmBB(data, 500);
%visualize the learned weights
visualize(model.W);
Do classification:
model= rbmFit(data, 500, labels);
prediction= rbmPredict(model, testdata);
Train a Deep Belief Network with 500,500,2000 architecture for classification:
models= dbnFit(data, [500 500 2000], labels);
prediction= dbnPredict(models, testdata);
see included example code for more
I can be contacted on andrej.karpathy@ gmail.
NOTE: This was a class project that I worked on for 1 month and then abandoned development for almost 4 years ago. Please do not send me specific questions about issues with the code or questions on how to do something. I only put this code online in hope that it can be useful to others but cannot fully support it.
If you would like pointers to more actively maintained implementations, have a look here (https://github.com/rasmusbergpalm/DeepLearnToolbox) or maybe here (https://github.com/lisa-lab/DeepLearningTutorials)
Sorry and best of luck!
原文：http://code.google.com/p/matrbm/
Code provided by Ruslan Salakhutdinov and Geoff Hinton
Permission is granted for anyone to copy, use, modify, or distribute this program and accompanying programs and documents for any purpose, provided this copyright notice is retained and prominently displayed, along with a note saying that the original programs are available from our web page. The programs and documents are distributed without any warranty, express or implied. As the programs were written for research purposes only, they have not been tested to the degree that would be advisable in any important application. All use of these programs is entirely at the user's own risk.
How to make it work:
1. Create a separate directory and download all these files into the same directory
2. Download from http://yann.lecun.com/exdb/mnist the following 4 files:
o train-images-idx3-ubyte.gz
o train-labels-idx1-ubyte.gz
o t10k-images-idx3-ubyte.gz
o t10k-labels-idx1-ubyte.gz
3. Unzip these 4 files by executing:
o gunzip train-images-idx3-ubyte.gz
o gunzip train-labels-idx1-ubyte.gz
o gunzip t10k-images-idx3-ubyte.gz
o gunzip t10k-labels-idx1-ubyte.gz
If unzipping with WinZip, make sure the file names have not been changed by Winzip.
4. Download Conjugate Gradient code minimize.m
5. Download Autoencoder_Code.tar which contains 13 files OR
download each of the following 13 files separately for training an autoencoder and a classification model:
o mnistdeepauto.m Main file for training deep autoencoder
o mnistclassify.m Main file for training classification model
o converter.m Converts raw MNIST digits into matlab format
o rbm.m Training RBM with binary hidden and binary visible units
o rbmhidlinear.m Training RBM with Gaussian hidden and binary visible units
o backprop.m Backpropagation for fine-tuning an autoencoder
o backpropclassify.m Backpropagation for classification using "encoder" network
o CG_MNIST.m Conjugate Gradient optimization for fine-tuning an autoencoder
o CG_CLASSIFY_INIT.m Conjugate Gradient optimization for classification (training top-layer weights while holding low-level weights fixed)
o CG_CLASSIFY.m Conjugate Gradient optimization for classification (training all weights)
o makebatches.m Creates minibatches for RBM training
o mnistdisp.m Displays progress during fine-tuning stage
o README.txt
6. For training a deep autoencoder run mnistdeepauto.m in matlab.
7. For training a classification model run mnistclassify.m in matlab.
8. Make sure you have enough space to store the entire MNIST dataset on your disk. You can also set various parameters in the code, such as maximum number of epochs, learning rates, network architecture, etc.
