Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
adc9500
commit 77716f2
Showing
12 changed files
with
1,468 additions
and
0 deletions.
There are no files selected for viewing
108 changes: 108 additions & 0 deletions
108
doc/ipython-notebooks/neuralnets/neuralnets_digits.ipynb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,108 @@ | ||
{ | ||
"metadata": { | ||
"name": "neuralnets_digits" | ||
}, | ||
"nbformat": 3, | ||
"nbformat_minor": 0, | ||
"worksheets": [ | ||
{ | ||
"cells": [ | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": {}, | ||
"source": [ | ||
"#Neural Networks for digit classification\n", | ||
"##by Khaled Nasr\n" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": {}, | ||
"source": [ | ||
"This notebook illustrates how to use the NeuralNets module for digit classification. We'll use the USPS dataset of handwritten digits to train and test a neural network." | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"collapsed": false, | ||
"input": [ | ||
"import numpy as np\n", | ||
"from scipy.io import loadmat\n", | ||
"from modshogun import NeuralNetwork\n", | ||
"from modshogun import NeuralLogisticLayer\n", | ||
"from modshogun import DynamicObjectArray\n", | ||
"from modshogun import RealFeatures\n", | ||
"\n", | ||
"# load the dataset\n", | ||
"dataset = loadmat('../../../data/multiclass/usps.mat')\n", | ||
"\n", | ||
"Xall = dataset['data']\n", | ||
"# the usps dataset has the digits labeled from 1 to 10 \n", | ||
"# we'll subtract 1 to make them in the 0-9 range instead\n", | ||
"Yall = dataset['label']-1 \n", | ||
"\n", | ||
"# the neural network will have 10 neurons in its output layer, one for each digit\n", | ||
"# therefore we need to give it the label for each example needs to be a vector of 10 elements\n", | ||
"Yall_expanded = np.eye(10)[:,np.squeeze(Yall)]\n", | ||
"\n", | ||
"# use the first 5000 examples for training, the rest will be used for testing\n", | ||
"Xtrain = Xall[:,0:5000]\n", | ||
"Ytrain = Yall_expanded[:,0:5000]\n", | ||
"\n", | ||
"# setup the network's layers\n", | ||
"layers = DynamicObjectArray()\n", | ||
"layers.append_element(NeuralLogisticLayer(50)) # 50 neurons in the hidden layer\n", | ||
"layers.append_element(NeuralLogisticLayer(10)) # 10 neurons in the output layer\n", | ||
"\n", | ||
"# create the network\n", | ||
"net = NeuralNetwork()\n", | ||
"net.initialize(256, layers) # 256 inputs, one for each pixel (images in the dataset are 16*16 pixels)\n", | ||
"\n", | ||
"# turn on regularization to reduce overfitting\n", | ||
"net.set_L2_regularization(0.001)\n", | ||
"\n", | ||
"# train the network, the error each iteration is printed to the console\n", | ||
"net.train_gradient_descent(RealFeatures(Xtrain), \n", | ||
" RealFeatures(Ytrain),\n", | ||
" 300, # number of iterations over the training set\n", | ||
" 1000); # mini-batch size\n", | ||
"\n", | ||
"# prepere the test set\n", | ||
"Xtest = Xall[:,5001:-1]\n", | ||
"Ytest = Yall[:,5001:-1]\n", | ||
"\n", | ||
"# apply the network to the test inputs\n", | ||
"predictions = net.apply(RealFeatures(Xtest)).get_feature_matrix()\n", | ||
"predictions = np.argmax(predictions, axis=0)\n", | ||
"\n", | ||
"# measure the test error\n", | ||
"test_error = float(np.sum(predictions!=Ytest))/Ytest.shape[1] * 100\n", | ||
"\n", | ||
"print \"Test Error =\", test_error, \"%\"" | ||
], | ||
"language": "python", | ||
"metadata": {}, | ||
"outputs": [ | ||
{ | ||
"output_type": "stream", | ||
"stream": "stdout", | ||
"text": [ | ||
"Test Error = 8.58938547486 %\n" | ||
] | ||
} | ||
], | ||
"prompt_number": 4 | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"collapsed": false, | ||
"input": [], | ||
"language": "python", | ||
"metadata": {}, | ||
"outputs": [] | ||
} | ||
], | ||
"metadata": {} | ||
} | ||
] | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,23 @@ | ||
/* | ||
* This program is free software; you can redistribute it and/or modify | ||
* it under the terms of the GNU General Public License as published by | ||
* the Free Software Foundation; either version 3 of the License, or | ||
* (at your option) any later version. | ||
* | ||
* Written (W) Khaled Nasr | ||
*/ | ||
|
||
%newobject apply(); | ||
|
||
/* Remove C Prefix */ | ||
%rename(NeuralNetwork) CNeuralNetwork; | ||
%rename(NeuralLayer) CNeuralLayer; | ||
%rename(NeuralLinearLayer) CNeuralLinearLayer; | ||
%rename(NeuralLogisticLayer) CNeuralLogisticLayer; | ||
|
||
/* Include Class Headers to make them visible from within the target language */ | ||
%include <shogun/neuralnets/NeuralNetwork.h> | ||
%include <shogun/neuralnets/NeuralLayer.h> | ||
%include <shogun/neuralnets/NeuralLinearLayer.h> | ||
%include <shogun/neuralnets/NeuralLogisticLayer.h> | ||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,7 @@ | ||
%{ | ||
#include <shogun/neuralnets/NeuralNetwork.h> | ||
#include <shogun/neuralnets/NeuralLayer.h> | ||
#include <shogun/neuralnets/NeuralLinearLayer.h> | ||
#include <shogun/neuralnets/NeuralLogisticLayer.h> | ||
%} | ||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,95 @@ | ||
/* | ||
* This program is free software; you can redistribute it and/or modify | ||
* it under the terms of the GNU General Public License as published by | ||
* the Free Software Foundation; either version 3 of the License, or | ||
* (at your option) any later version. | ||
* | ||
* Written (W) 2014 Khaled Nasr | ||
*/ | ||
|
||
#include <shogun/base/Parameter.h> | ||
#include <shogun/neuralnets/NeuralLayer.h> | ||
|
||
using namespace shogun; | ||
|
||
CNeuralLayer::CNeuralLayer() | ||
: CSGObject(), m_num_neurons(0) | ||
{ | ||
init(); | ||
} | ||
|
||
|
||
CNeuralLayer::CNeuralLayer(int32_t num_neurons) | ||
: CSGObject(), m_num_neurons(num_neurons) | ||
{ | ||
init(); | ||
} | ||
|
||
CNeuralLayer::CNeuralLayer(const CNeuralLayer& orig) : CSGObject() | ||
{ | ||
shallow_copy(orig); | ||
init(); | ||
} | ||
|
||
|
||
CNeuralLayer::~CNeuralLayer() | ||
{ | ||
} | ||
|
||
void CNeuralLayer::initialize(int32_t previous_layer_num_neurons) | ||
{ | ||
m_previous_layer_num_neurons = previous_layer_num_neurons; | ||
} | ||
|
||
void CNeuralLayer::set_batch_size(int32_t batch_size) | ||
{ | ||
m_batch_size = batch_size; | ||
|
||
if (m_activations.vector!=NULL) SG_FREE(m_activations.vector); | ||
if (m_input_gradients.vector!=NULL) SG_FREE(m_input_gradients.vector); | ||
if (m_local_gradients.vector!=NULL) SG_FREE(m_local_gradients.vector); | ||
|
||
m_activations.vlen = m_num_neurons * m_batch_size; | ||
m_input_gradients.vlen = m_previous_layer_num_neurons * m_batch_size; | ||
m_local_gradients.vlen = m_num_neurons * m_batch_size; | ||
|
||
m_activations.vector = SG_MALLOC(float64_t, m_activations.vlen); | ||
m_input_gradients.vector = SG_MALLOC(float64_t, m_input_gradients.vlen); | ||
m_local_gradients.vector = SG_MALLOC(float64_t, m_local_gradients.vlen); | ||
} | ||
|
||
void CNeuralLayer::init() | ||
{ | ||
SG_ADD(&m_num_neurons, "num_neurons", | ||
"Number of Neurons", MS_NOT_AVAILABLE); | ||
SG_ADD(&m_previous_layer_num_neurons, "previous_layer_num_neurons", | ||
"Number of neurons in the previous layer", MS_NOT_AVAILABLE); | ||
SG_ADD(&m_batch_size, "batch_size", | ||
"Batch Size", MS_NOT_AVAILABLE); | ||
SG_ADD(&m_activations, "activations", | ||
"Activations", MS_NOT_AVAILABLE); | ||
SG_ADD(&m_input_gradients, "input_gradients", | ||
"Input Gradients", MS_NOT_AVAILABLE); | ||
SG_ADD(&m_local_gradients, "local_gradients", | ||
"Local Gradients", MS_NOT_AVAILABLE); | ||
} | ||
|
||
void CNeuralLayer::shallow_copy(const CNeuralLayer &orig) | ||
{ | ||
m_num_neurons = orig.m_num_neurons; | ||
m_previous_layer_num_neurons = orig.m_previous_layer_num_neurons; | ||
m_batch_size = orig.m_batch_size; | ||
m_activations = SGVector<float64_t>(orig.m_activations); | ||
m_input_gradients = SGVector<float64_t>(orig.m_input_gradients); | ||
m_local_gradients = SGVector<float64_t>(orig.m_local_gradients); | ||
} | ||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
Oops, something went wrong.