+++ /dev/null
-/*
- * mlp-mnist is an implementation of a multi-layer neural network.
- *
- * Copyright (c) 2006 École Polytechnique Fédérale de Lausanne,
- * http://www.epfl.ch
- *
- * Written by Francois Fleuret <francois@fleuret.org>
- *
- * This file is part of mlp-mnist.
- *
- * mlp-mnist is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 3 as
- * published by the Free Software Foundation.
- *
- * mlp-mnist is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with mlp-mnist. If not, see <http://www.gnu.org/licenses/>.
- *
- */
-
-// LeCun et al. 1998:
-
-// 2-layer NN, 300 hidden units, mean square error 4.70%
-// 2-layer NN, 1000 hidden units 4.50%
-// 3-layer NN, 300+100 hidden units 3.05%
-// 3-layer NN, 500+150 hidden units 2.95%
-
-/*********************************************************************
-
- This program, trained on 20,000 (+ 20,000 for the stopping
- criterion), tested on the 10,000 of the MNIST test set 100 hidden
- neurons, basic network, 3.48%
-
- TRAINING
-
- ./ann --nb-training-examples 20000 --nb-validation-examples 20000 \
- --mlp-structure 784,200,10 \
- --data-files ${DATA_DIR}/train-images-idx3-ubyte ${DATA_DIR}/train-labels-idx1-ubyte \
- --save-mlp simple.mlp
-
- TEST
-
- ./ann --load-mlp simple.mlp \
- --data-files ${DATA_DIR}/t10k-images-idx3-ubyte ${DATA_DIR}/t10k-labels-idx1-ubyte \
- --nb-test-examples 10000
-
-*********************************************************************/
-
-#include <iostream>
-#include <fstream>
-#include <cmath>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-
-using namespace std;
-
-#include "images.h"
-#include "neural.h"
-
-#define SMALL_BUFFER_SIZE 1024
-
-//////////////////////////////////////////////////////////////////////
-// Global Variables
-//////////////////////////////////////////////////////////////////////
-
-int nb_experiment = 0;
-int nb_training_examples = 0;
-int nb_validation_examples = 0;
-int nb_test_examples = 0;
-bool save_data = false;
-
-char images_filename[SMALL_BUFFER_SIZE] = "\0";
-char labels_filename[SMALL_BUFFER_SIZE] = "\0";
-char opt_load_filename[SMALL_BUFFER_SIZE] = "\0";
-char opt_save_filename[SMALL_BUFFER_SIZE] = "\0";
-char opt_layer_sizes[SMALL_BUFFER_SIZE] = "\0";
-
-char *next_word(char *buffer, char *r, int buffer_size) {
- char *s;
- s = buffer;
- if(r != NULL)
- {
- if(*r == '"') {
- r++;
- while((*r != '"') && (*r != '\0') &&
- (s<buffer+buffer_size-1))
- *s++ = *r++;
- if(*r == '"') r++;
- } else {
- while((*r != '\r') && (*r != '\n') && (*r != '\0') &&
- (*r != '\t') && (*r != ' ') && (*r != ',') &&
- (s<buffer+buffer_size-1))
- *s++ = *r++;
- }
-
- while((*r == ' ') || (*r == '\t') || (*r == ',')) r++;
- if((*r == '\0') || (*r=='\r') || (*r=='\n')) r = NULL;
- }
- *s = '\0';
- return r;
-}
-
-//////////////////////////////////////////////////////////////////////
-// Simple routine to check we have enough parameters
-//////////////////////////////////////////////////////////////////////
-
-void check_opt(int argc, char **argv, int n_opt, int n, const char *help) {
- if(n_opt + n >= argc) {
- cerr << "Missing argument for " << argv[n_opt] << ".\n";
- cerr << "Expecting " << help << ".\n";
- exit(1);
- }
-}
-
-void print_help_and_exit(int e) {
- cout << "ANN. Written by François Fleuret.\n";
- cout << "$Id: ann.cc,v 1.1 2005-12-13 17:19:11 fleuret Exp $\n";
- cout<< "\n";
- exit(e);
-}
-
-int main(int argc, char **argv) {
-
- if(argc == 1) print_help_and_exit(1);
-
- nice(10);
-
- // Parsing the command line parameters ///////////////////////////////
-
- int i = 1;
-
- while(i < argc) {
-
- if(argc == 1 || strcmp(argv[i], "--help") == 0) print_help_and_exit(0);
-
- else if(strcmp(argv[i], "--data-files") == 0) {
- check_opt(argc, argv, i, 2, "<string: pixel filename> <string: label filename>");
- strncpy(images_filename, argv[i+1], SMALL_BUFFER_SIZE);
- strncpy(labels_filename, argv[i+2], SMALL_BUFFER_SIZE);
- i += 3;
- }
-
- else if(strcmp(argv[i], "--load-mlp") == 0) {
- check_opt(argc, argv, i, 1, "<string: mlp filename>");
- strncpy(opt_load_filename, argv[i+1], SMALL_BUFFER_SIZE);
- i += 2;
- }
-
- else if(strcmp(argv[i], "--mlp-structure") == 0) {
- check_opt(argc, argv, i, 1, "<int: input layer size>,<int: first hidden layer size>,[...,]<int: output layer size>");
- strncpy(opt_layer_sizes, argv[i+1], SMALL_BUFFER_SIZE);
- i += 2;
- }
-
- else if(strcmp(argv[i], "--save-mlp") == 0) {
- check_opt(argc, argv, i, 1, "<string: mlp filename>");
- strncpy(opt_save_filename, argv[i+1], SMALL_BUFFER_SIZE);
- i += 2;
- }
-
- else if(strcmp(argv[i], "--nb-experiment") == 0) {
- check_opt(argc, argv, i, 1, "<int: number of the experiment>");
- nb_experiment = atoi(argv[i+1]);
- i += 2;
- }
-
- else if(strcmp(argv[i], "--nb-training-examples") == 0) {
- check_opt(argc, argv, i, 1, "<int: number of examples for the training>");
- nb_training_examples = atoi(argv[i+1]);
- i += 2;
- }
-
- else if(strcmp(argv[i], "--nb-validation-examples") == 0) {
- check_opt(argc, argv, i, 1, "<int: number of examples for the validation>");
- nb_validation_examples = atoi(argv[i+1]);
- i += 2;
- }
-
- else if(strcmp(argv[i], "--nb-test-examples") == 0) {
- check_opt(argc, argv, i, 1, "<int: number of examples for the test>");
- nb_test_examples = atoi(argv[i+1]);
- i += 2;
- }
-
- else if(strcmp(argv[i], "--save-data") == 0) {
- save_data = true;
- i++;
- }
-
- else {
- cerr << "Unknown option " << argv[i] << "\n";
- print_help_and_exit(1);
- }
- }
-
- ImageSet image_set;
- cout << "Loading the data file ..."; cout.flush();
- image_set.load_mnist_format(images_filename, labels_filename);
- cout << " done.\n"; cout.flush();
-
- cout << "Database contains " << image_set.nb_pics()
- << " images of resolution " << image_set.width() << "x" << image_set.height()
- << " divided into " << image_set.nb_obj() << " objects.\n";
-
- srand48(nb_experiment);
-
- int nb_layers = 0;
- int *layer_sizes = 0;
-
- if(opt_layer_sizes[0]) {
- char *s = opt_layer_sizes;
- char token[SMALL_BUFFER_SIZE];
- while(s) { s = next_word(token, s, SMALL_BUFFER_SIZE); nb_layers++; }
-
- if(nb_layers < 2) {
- cerr << "Need at least two layers.\n";
- exit(1);
- }
-
- layer_sizes = new int[nb_layers];
- s = opt_layer_sizes;
- int n = 0;
- while(s) { s = next_word(token, s, SMALL_BUFFER_SIZE); layer_sizes[n++] = atoi(token); }
- }
-
- // Loading or creating a perceptron from scratch /////////////////////
-
- MultiLayerPerceptron *mlp = 0;
-
- if(opt_load_filename[0]) {
-
- ifstream stream(opt_load_filename);
- if(stream.fail()) {
- cerr << "Can not read " << opt_load_filename << ".\n";
- exit(1);
- }
-
- cout << "Loading network " << opt_load_filename << " ... "; cout.flush();
- mlp = new MultiLayerPerceptron(stream);
- cout << "done (layers of sizes";
- for(int l = 0; l < mlp->nb_layers(); l++) cout << " " << mlp->layer_size(l);
- cout << ")\n"; cout.flush();
-
- } else if(nb_layers > 0) {
-
- if(layer_sizes[0] != image_set.width() * image_set.height() ||
- layer_sizes[nb_layers-1] != image_set.nb_obj()) {
- cerr << "For this data set, the input layer has to be of size " << image_set.width() * image_set.height() << ",\n";
- cerr << "and the output has to be of size " << image_set.nb_obj() << ".\n";
- exit(1);
- }
-
- cout << "Creating a new network (layers of sizes";
- for(int i = 0; i < nb_layers; i++) cout << " " << layer_sizes[i];
- cout << ").\n";
-
- mlp = new MultiLayerPerceptron(nb_layers, layer_sizes);
- mlp->init_random_weights(1e-1);
- }
-
- // Training the perceptron ///////////////////////////////////////////
-
- ImageSet training_set, validation_set, test_set;
-
- if(nb_training_examples > 0)
- training_set.sample_among_unused_pictures(image_set, nb_training_examples);
-
- if(nb_validation_examples > 0)
- validation_set.sample_among_unused_pictures(image_set, nb_validation_examples);
-
- if(save_data && mlp) mlp->save_data();
-
- if(nb_training_examples > 0) {
- if(validation_set.nb_pics() == 0) {
- cerr << "We need validation pictures for training.\n";
- exit(1);
- }
- cout << "Training the network with " << nb_training_examples << " training and " << nb_validation_examples << " validation examples.\n"; cout.flush();
- mlp->train(&training_set, &validation_set);
- }
-
- // Saving the perceptron /////////////////////////////////////////////
-
- if(opt_save_filename[0]) {
- if(!mlp) {
- cerr << "No perceptron to save.\n";
- exit(1);
- }
-
- ofstream stream(opt_save_filename);
- if(stream.fail()) {
- cerr << "Can not write " << opt_save_filename << ".\n";
- exit(1);
- }
-
- cout << "Saving network " << opt_save_filename << " ... "; cout.flush();
- mlp->save(stream);
- cout << "done.\n"; cout.flush();
- }
-
- // Testing the perceptron ////////////////////////////////////////////
-
- if(nb_test_examples > 0) {
- test_set.sample_among_unused_pictures(image_set, nb_test_examples);
- cout << "Error rate " << mlp->error(&test_set) << " (" << mlp->classification_error(&test_set)*100 << "%)\n";
-
- // This is to test the analytical gradient
- // scalar_t gradient[mlp->nb_weights()], numerical_gradient[mlp->nb_weights()];
- // mlp->compute_gradient(&test_set, gradient);
- // mlp->compute_numerical_gradient(&test_set, numerical_gradient);
- // for(int i = 0; i < mlp->nb_weights(); i++) cout << "TEST " << gradient[i] << " " << numerical_gradient[i] << "\n";
- }
-
- // Flushing the log //////////////////////////////////////////////////
-
- delete[] layer_sizes;
-}