FANN_EXTERNAL void FANN_API fann_cascadetrain_on_file(struct fann *ann, const char *filename,
unsigned int max_neurons,
unsigned int neurons_between_reports,
float desired_error)
{
struct fann_train_data *data = fann_read_train_from_file(filename);
if(data == NULL)
{
return;
}
fann_cascadetrain_on_data(ann, data, max_neurons, neurons_between_reports, desired_error);
fann_destroy_train(data);
}
int main()
{
struct fann *ann;
struct fann_train_data *train_data, *test_data;
const float desired_error = (const float) 0.001;
unsigned int max_neurons = 40;
unsigned int neurons_between_reports = 1;
printf("Reading data.\n");
train_data = fann_read_train_from_file("../benchmarks/datasets/two-spiral.train");
test_data = fann_read_train_from_file("../benchmarks/datasets/two-spiral.test");
fann_scale_train_data(train_data, 0, 1);
fann_scale_train_data(test_data, 0, 1);
printf("Creating network.\n");
ann = fann_create_shortcut(2, fann_num_input_train_data(train_data), fann_num_output_train_data(train_data));
fann_set_training_algorithm(ann, FANN_TRAIN_RPROP);
fann_set_activation_function_hidden(ann, FANN_SIGMOID_SYMMETRIC);
fann_set_activation_function_output(ann, FANN_LINEAR_PIECE);
fann_set_train_error_function(ann, FANN_ERRORFUNC_LINEAR);
fann_print_parameters(ann);
printf("Training network.\n");
fann_cascadetrain_on_data(ann, train_data, max_neurons, neurons_between_reports, desired_error);
fann_print_connections(ann);
printf("\nTrain error: %f, Test error: %f\n\n", fann_test_data(ann, train_data),
fann_test_data(ann, test_data));
printf("Saving network.\n");
fann_save(ann, "two_spirali.net");
printf("Cleaning up.\n");
fann_destroy_train(train_data);
fann_destroy_train(test_data);
fann_destroy(ann);
return 0;
}
int main()
{
struct fann *ann;
struct fann_train_data *train_data, *test_data;
const float desired_error = (const float)0.0;
unsigned int max_neurons = 30;
unsigned int neurons_between_reports = 1;
unsigned int bit_fail_train, bit_fail_test;
float mse_train, mse_test;
unsigned int i = 0;
fann_type *output;
fann_type steepness;
int multi = 0;
enum fann_activationfunc_enum activation;
enum fann_train_enum training_algorithm = FANN_TRAIN_RPROP;
printf("Reading data.\n");
train_data = fann_read_train_from_file("../benchmarks/datasets/parity8.train");
test_data = fann_read_train_from_file("../benchmarks/datasets/parity8.test");
fann_scale_train_data(train_data, -1, 1);
fann_scale_train_data(test_data, -1, 1);
printf("Creating network.\n");
ann = fann_create_shortcut(2, fann_num_input_train_data(train_data), fann_num_output_train_data(train_data));
fann_set_training_algorithm(ann, training_algorithm);
fann_set_activation_function_hidden(ann, FANN_SIGMOID_SYMMETRIC);
fann_set_activation_function_output(ann, FANN_LINEAR);
fann_set_train_error_function(ann, FANN_ERRORFUNC_LINEAR);
if(!multi)
{
/*steepness = 0.5;*/
steepness = 1;
fann_set_cascade_activation_steepnesses(ann, &steepness, 1);
/*activation = FANN_SIN_SYMMETRIC;*/
activation = FANN_SIGMOID_SYMMETRIC;
fann_set_cascade_activation_functions(ann, &activation, 1);
fann_set_cascade_num_candidate_groups(ann, 8);
}
if(training_algorithm == FANN_TRAIN_QUICKPROP)
{
fann_set_learning_rate(ann, 0.35);
fann_randomize_weights(ann, -2.0,2.0);
}
fann_set_bit_fail_limit(ann, 0.9);
fann_set_train_stop_function(ann, FANN_STOPFUNC_BIT);
fann_print_parameters(ann);
fann_save(ann, "cascade_train2.net");
printf("Training network.\n");
fann_cascadetrain_on_data(ann, train_data, max_neurons, neurons_between_reports, desired_error);
fann_print_connections(ann);
mse_train = fann_test_data(ann, train_data);
bit_fail_train = fann_get_bit_fail(ann);
mse_test = fann_test_data(ann, test_data);
bit_fail_test = fann_get_bit_fail(ann);
printf("\nTrain error: %f, Train bit-fail: %d, Test error: %f, Test bit-fail: %d\n\n",
mse_train, bit_fail_train, mse_test, bit_fail_test);
for(i = 0; i < train_data->num_data; i++)
{
output = fann_run(ann, train_data->input[i]);
if((train_data->output[i][0] >= 0 && output[0] <= 0) ||
(train_data->output[i][0] <= 0 && output[0] >= 0))
{
printf("ERROR: %f does not match %f\n", train_data->output[i][0], output[0]);
}
}
printf("Saving network.\n");
fann_save(ann, "cascade_train.net");
printf("Cleaning up.\n");
fann_destroy_train(train_data);
fann_destroy_train(test_data);
fann_destroy(ann);
return 0;
}
int main()
{
fann_type *calc_out;
const unsigned int num_input = 22500;
const unsigned int num_output = 1;
//const unsigned int num_layers = 4;
const unsigned int num_layers = 4;
/* this value can be changed to tweak the network */
const unsigned int num_neurons_hidden = 50;
//const unsigned int num_neurons_hidden = 150;
const float desired_error = (const float) 0.02;
const unsigned int max_epochs = 15000;
const unsigned int epochs_between_reports = 20;
float learning_rate = .5;
struct fann *ann;
struct fann_train_data *data;
int num_neurons = 0;
unsigned int i = 0;
unsigned int decimal_point;
/* CREATING NETWORK */
ann = fann_create_shortcut(2, num_input, num_output);
/* reading training data */
data = fann_read_train_from_file("training.data");
//fann_set_cascade_activation_steepness_hidden(ann, 1);
//fann_set_cascade_activation_steepness_output(ann, 1);
//fann_set_cascade_activation_steepnesses(ann, 1);
fann_set_activation_function_hidden(ann, FANN_SIGMOID_SYMMETRIC);
fann_set_activation_function_output(ann, FANN_SIGMOID_SYMMETRIC);
fann_init_weights(ann, data);
/*
TRAINING NETWORK
run x epochs at learn rate .y
*/
//fann_cascadetrain_on_data(ann, data, 2000, epochs_between_reports, .4);
fann_set_learning_rate(ann, .7);
fann_cascadetrain_on_data(ann, data, 2000, epochs_between_reports, .0002);
//fann_train_on_data(ann, data, 500, epochs_between_reports, .002);
/*fann_set_learning_rate(ann, .5);
fann_cascadetrain_on_data(ann, data,5000, epochs_between_reports, .2);
//fann_train_on_data(ann, data,50, epochs_between_reports, .2);
fann_set_learning_rate(ann, .2);
fann_cascadetrain_on_data(ann, data,1000, epochs_between_reports, .15);
//fann_train_on_data(ann, data,100, epochs_between_reports, .15);
fann_set_learning_rate(ann, .1);
//fann_train_on_data(ann, data,5000, epochs_between_reports, .002);
fann_cascadetrain_on_data(ann, data,200, epochs_between_reports, .00002);
*/
/* TESTING NETWORK */
printf("Testing network. %f\n", fann_test_data(ann, data));
for(i = 0; i < fann_length_train_data(data); i++)
{
calc_out = fann_run(ann, data->input[i]);
printf("%f, should be %f, difference=%f\n",
calc_out[0], data->output[i][0],
fann_abs(calc_out[0] - data->output[i][0]));
}
/* SAVING NETWORK */
fann_save(ann, "image_spam.net");
/* CLEANING UP */
fann_destroy_train(data);
fann_destroy(ann);
return 0;
}
int ViFann::train(const bool &debug)
{
if(mTrain == NULL)
{
LOG("The training dataset was not created. No training will be done.");
return -1;
}
int reportEpochs = 0;
if(ENABLE_CALLBACK) reportEpochs = 1;
if(debug)
{
if(mTraining == Cascade)
{
#ifndef GPU
if(mTrainStagnationIterations >= 0)
{
fann_set_cascade_output_change_fraction(mNetwork, mTrainStagnationFraction);
fann_set_cascade_output_stagnation_epochs(mNetwork, mTrainStagnationIterations);
fann_set_cascade_candidate_change_fraction(mNetwork, mTrainStagnationFraction);
fann_set_cascade_candidate_stagnation_epochs(mNetwork, mTrainStagnationIterations);
}
fann_cascadetrain_on_data(mNetwork, mTrain->data(), mTrainNeurons, 1, mTrainMse);
#endif
}
else if(mTrainStagnationIterations < 0) (this->*fannTrainManyPointer)(mNetwork, mTrain->data(), mTrainEpochs, 1, mTrainMse);
else
{
int i, counter = 0;
qreal previousMse, mse, difference;
for(i = 1; i <= mTrainEpochs; ++i)
{
mse = (this->*fannTrainSinglePointer)(mNetwork, mTrain->data());
difference = abs(previousMse - mse);
previousMse = mse;
LOG("Current epoch: " + QString::number(i) + "\t\tCurrent MSE: " + QString::number(mse, 'f', 10) + "\tMSE change fraction: " + QString::number(difference, 'f', 10) + " (desired: " + QString::number(mTrainStagnationFraction, 'f', 10) + ")");
if(mse <= mTrainMse)
{
LOG("The minimum MSE was reached. Training was stopped.");
break;
}
if(difference <= mTrainStagnationFraction)
{
if(counter >= mTrainStagnationIterations)
{
LOG("Training has stagnated with a MSE change fraction of " + QString::number(difference, 'f', 10) + ". Training was stopped.");
break;
}
++counter;
}
else counter = 0;
}
delete mTrain;
mTrain = NULL;
return i - 1;
}
}
else
{
if(mTraining == Cascade)
{
#ifndef GPU
if(mTrainStagnationIterations >= 0)
{
fann_set_cascade_output_change_fraction(mNetwork, mTrainStagnationFraction);
fann_set_cascade_output_stagnation_epochs(mNetwork, mTrainStagnationIterations);
fann_set_cascade_candidate_change_fraction(mNetwork, mTrainStagnationFraction);
fann_set_cascade_candidate_stagnation_epochs(mNetwork, mTrainStagnationIterations);
}
fann_cascadetrain_on_data(mNetwork, mTrain->data(), mTrainNeurons, reportEpochs, mTrainMse);
#endif
}
else if(mTrainStagnationIterations < 0) (this->*fannTrainManyPointer)(mNetwork, mTrain->data(), mTrainEpochs, reportEpochs, mTrainMse);
else
{
int i, counter = 0;
qreal previousMse, mse, difference;
for(i = 1; i <= mTrainEpochs; ++i)
{
mse = (this->*fannTrainSinglePointer)(mNetwork, mTrain->data());
if(mse <= mTrainMse) break;
difference = abs(previousMse - mse);
previousMse = mse;
if(difference <= mTrainStagnationFraction)
{
if(counter >= mTrainStagnationIterations) break;
++counter;
}
else counter = 0;
}
delete mTrain;
mTrain = NULL;
return i - 1;
}
}
delete mTrain;
mTrain = NULL;
return -1;
}
int main(int argc,char **argv)
{
unlink(histfile);
srand ( time ( NULL ) );
// printf ( "Reading data.\n" );
train_data = fann_read_train_from_file ( "train.dat" );
test_data = fann_read_train_from_file ( "test.dat" );
// signal ( 2, sig_term );
// fann_scale_train_data ( train_data, 0, 1.54 );
// fann_scale_train_data ( test_data, 0, 1.54 );
//cln_test_data=fann_duplicate_train_data(test_data);
cln_train_data=fann_duplicate_train_data(train_data);
printf ( "Creating cascaded network.\n" );
ann =
fann_create_shortcut ( 2, fann_num_input_train_data ( train_data ),
fann_num_output_train_data ( train_data ) );
fann_set_training_algorithm ( ann, FANN_TRAIN_RPROP );
fann_set_activation_function_hidden ( ann, FANN_SIGMOID );
fann_set_activation_function_output ( ann, FANN_SIGMOID);
fann_set_train_error_function ( ann, FANN_ERRORFUNC_LINEAR );
// if (fann_set_scaling_params(ann, train_data,-1.0f,1.0f,0.0f, 1.0f)==-1)
// printf("set scaling error: %s\n",fann_get_errno((struct fann_error*)ann));
// fann_scale_train_input(ann,train_data);
// fann_scale_output_train_data(train_data,0.0f,1.0f);
// fann_scale_input_train_data(train_data, -1.0,1.0f);
// fann_scale_output_train_data(test_data,-1.0f,1.0f);
// fann_scale_input_train_data(test_data, -1.0,1.0f);
//fann_scale_train(ann,train_data);
// fann_scale_train(ann,weight_data);
// fann_scale_train(ann,test_data);
/*
* fann_set_cascade_output_change_fraction(ann, 0.1f);
* ;
* fann_set_cascade_candidate_change_fraction(ann, 0.1f);
*
*/
// fann_set_cascade_output_stagnation_epochs ( ann, 180 );
//fann_set_cascade_weight_multiplier ( ann, ( fann_type ) 0.1f );
fann_set_callback ( ann, cascade_callback );
if ( !multi )
{
/* */
// steepness[0] = 0.22;
steepness[0] = 0.9;
steepness[1] = 1.0;
/*
* steepness[1] = 0.55;
* ;
* steepness[1] = 0.33;
* ;
* steepness[3] = 0.11;
* ;
* steepness[1] = 0.01;
*
*/
/*
* steepness = 0.5;
*
*/
// fann_set_cascade_activation_steepnesses ( ann, steepness, 2);
/*
* activation = FANN_SIN_SYMMETRIC;
*/
/*
* activation[0] = FANN_SIGMOID;
*
*/
activation[0] = FANN_SIGMOID;
/*
* activation[2] = FANN_ELLIOT_SYMMETRIC;
*
*/
activation[1] = FANN_LINEAR_PIECE;
/*
* activation[4] = FANN_GAUSSIAN_SYMMETRIC;
* ;
* activation[5] = FANN_SIGMOID;
*
*/
activation[2] = FANN_ELLIOT;
activation[3] = FANN_COS;
/*
*
*
*/
activation[4] = FANN_SIN;
fann_set_cascade_activation_functions ( ann, activation, 5);
/* fann_set_cascade_num_candidate_groups ( ann,
fann_num_input_train_data
( train_data ) ); */
}
else
{
/*
* fann_set_cascade_activation_steepnesses(ann, &steepness, 0.75);
*
*/
// fann_set_cascade_num_candidate_groups ( ann, 1 );
}
/* TODO: weight mult > 0.01 */
/* if ( training_algorithm == FANN_TRAIN_QUICKPROP )
{
fann_set_learning_rate ( ann, 0.35f );
}
else
{
fann_set_learning_rate ( ann, 0.7f );
}
fann_set_bit_fail_limit ( ann, ( fann_type ) 0.9f );*/
/*
* fann_set_train_stop_function(ann, FANN_STOPFUNC_BIT);
*
*/
//fann_scale_output_train_data(train_data,0.0f,1.0f);
//fann_scale_input_train_data(train_data, -1.0f,1.0f);
// fann_scale_output_train_data(test_data, 0.0f,1.0f);
//fann_scale_input_train_data(test_data, -1.0f,1.0f);
// fann_randomize_weights ( ann, -0.2f, 0.2f );
fann_init_weights ( ann, train_data );
printf ( "Training network.\n" );
fann_cascadetrain_on_data ( ann, train_data, max_neurons,
1, desired_error );
fann_print_connections ( ann );
mse_train = fann_test_data ( ann, train_data );
bit_fail_train = fann_get_bit_fail ( ann );
mse_test = fann_test_data ( ann, test_data );
bit_fail_test = fann_get_bit_fail ( ann );
printf
( "\nTrain error: %.08f, Train bit-fail: %d, Test error: %.08f, Test bit-fail: %d\n\n",
mse_train, bit_fail_train, mse_test, bit_fail_test );
printf ( "Saving cascaded network.\n" );
fann_save ( ann, "cascaded.net" );
// printf ( "Cleaning up.\n" );
fann_destroy_train ( train_data );
fann_destroy_train ( test_data );
fann_destroy ( ann );
return 0;
}
