/*
* Test a set of training data and calculate the MSE
*/
FANN_EXTERNAL float FANN_API fann_test_data(struct fann *ann, struct fann_train_data *data)
{
unsigned int i;
if(fann_check_input_output_sizes(ann, data) == -1)
return 0;
fann_reset_MSE(ann);
for(i = 0; i != data->num_data; i++)
{
fann_test(ann, data->input[i], data->output[i]);
}
return fann_get_MSE(ann);
}
float test_data_parallel(struct fann *ann, struct fann_train_data *data, const unsigned int threadnumb, vector< vector<fann_type> >& predicted_outputs)
{
if(fann_check_input_output_sizes(ann, data) == -1)
return 0;
predicted_outputs.resize(data->num_data,vector<fann_type> (data->num_output));
fann_reset_MSE(ann);
vector<struct fann *> ann_vect(threadnumb);
int i=0,j=0;
//generate copies of the ann
omp_set_dynamic(0);
omp_set_num_threads(threadnumb);
#pragma omp parallel private(j)
{
#pragma omp for schedule(static)
for(i=0; i<(int)threadnumb; i++)
{
ann_vect[i]=fann_copy(ann);
}
//parallel computing of the updates
#pragma omp for schedule(static)
for(i = 0; i < (int)data->num_data; ++i)
{
j=omp_get_thread_num();
fann_type* temp_predicted_output=fann_test(ann_vect[j], data->input[i],data->output[i]);
for(unsigned int k=0;k<data->num_output;++k)
{
predicted_outputs[i][k]=temp_predicted_output[k];
}
}
}
//merge of MSEs
for(i=0;i<(int)threadnumb;++i)
{
ann->MSE_value+= ann_vect[i]->MSE_value;
ann->num_MSE+=ann_vect[i]->num_MSE;
fann_destroy(ann_vect[i]);
}
return fann_get_MSE(ann);
}
/*
* Scale input and output data based on previously calculated parameters.
*/
FANN_EXTERNAL void FANN_API fann_descale_train( struct fann *ann, struct fann_train_data *data )
{
unsigned cur_sample;
if(ann->scale_mean_in == NULL)
{
fann_error( (struct fann_error *) ann, FANN_E_SCALE_NOT_PRESENT );
return;
}
/* Check that we have good training data. */
if(fann_check_input_output_sizes(ann, data) == -1)
return;
for( cur_sample = 0; cur_sample < data->num_data; cur_sample++ )
{
fann_descale_input( ann, data->input[ cur_sample ] );
fann_descale_output( ann, data->output[ cur_sample ] );
}
}
/*
* Train for one epoch with the selected training algorithm
*/
FANN_EXTERNAL float FANN_API fann_train_epoch(struct fann *ann, struct fann_train_data *data)
{
if(fann_check_input_output_sizes(ann, data) == -1)
return 0;
switch (ann->training_algorithm)
{
case FANN_TRAIN_QUICKPROP:
return fann_train_epoch_quickprop(ann, data);
case FANN_TRAIN_RPROP:
return fann_train_epoch_irpropm(ann, data);
case FANN_TRAIN_SARPROP:
return fann_train_epoch_sarprop(ann, data);
case FANN_TRAIN_BATCH:
return fann_train_epoch_batch(ann, data);
case FANN_TRAIN_INCREMENTAL:
return fann_train_epoch_incremental(ann, data);
}
return 0;
}
/*
* Train for one epoch with the selected training algorithm
*/
FANN_EXTERNAL float FANN_API fann_train_epoch(struct fann *ann, struct fann_train_data *data, struct fpts_cl *fptscl)
{
if(fann_check_input_output_sizes(ann, data) == -1)
return 0;
//sclWrite(fptscl->hardware, ann->total_connections*sizeof(fann_type), fptscl->weightscl, ann->weights);
//printf("wok. Enter train. fptscl->software_mulsum = %s, %d\n", fptscl->software_mulsum.kernelName, fptscl->hardware.deviceType);
switch (ann->training_algorithm)
{
case FANN_TRAIN_QUICKPROP:
return fann_train_epoch_quickprop(ann, data);
case FANN_TRAIN_RPROP:
return fann_train_epoch_irpropm(ann, data, fptscl);
case FANN_TRAIN_SARPROP:
return fann_train_epoch_sarprop(ann, data);
case FANN_TRAIN_BATCH:
return fann_train_epoch_batch(ann, data);
case FANN_TRAIN_INCREMENTAL:
return fann_train_epoch_incremental(ann, data);
}
return 0;
}
