int main ( int argc, char **argv ) { srand(time(NULL)); if ( argc<=1 ) { // printf ( "neuro num\r\n" ); // exit ( 0 ); } if (argc>2) { //desired_error=atof(argv[2]); numn=atoi(argv[1]); l1n=atoi(argv[2]); if (argc>3) l2n=atoi(argv[3]); if (argc>4) l3n=atoi(argv[4]); if (argc>5) l4n=atoi(argv[5]); if (argc>6) l5n=atoi(argv[6]); if (argc>7) l6n=atoi(argv[7]); } signal ( 2, sig_term ); srand ( time ( NULL ) ); printf("loading training data..."); train_data = fann_read_train_from_file ( "train.dat" ); test_data = fann_read_train_from_file ( "test.dat" ); weight_data=fann_merge_train_data(train_data,test_data); cln_weight_data=fann_duplicate_train_data(weight_data); cln_test_data=fann_duplicate_train_data(test_data); cln_train_data=fann_duplicate_train_data(train_data); //num_neurons_hidden = atoi ( argv[1] ); srand(time(NULL)); y=atoi(argv[2]); lay=atoi(argv[1]); ln=lay+2; if (lay==1) y2=train_data->num_output; best_perc=1; printf("\r\ndoing %ux%u [layers=%u,out=%u]",lay,y,ln, train_data->num_output); while (true) { neur1=1+(rand()%y); neur2=1+(rand()%y); conn_rate=0.5f+((rand()%50)*0.01f); printf("\r\n%2dx%-4d: ",neur1,neur2); // printf("create network: layers=%d l1n=%d l2n=%d l3n=%d l4n=%d\ l5n=%d l6n=%dr\n",numn,l1n,l2n,l3n,l4n,l5n,l6n); ann = fann_create_standard (//conn_rate, ln, train_data->num_input, neur1, neur2, train_data->num_output ); //fann_init_weights ( ann, train_data ); printf(" [%p] ",ann); if ( ( int ) ann==NULL ) { printf ( "error" ); exit ( 0 ); } fann_set_activation_function_hidden(ann,FANN_SIGMOID); fann_set_activation_function_output(ann,FANN_SIGMOID); rebuild_functions(neur1); fann_set_training_algorithm ( ann, FANN_TRAIN_RPROP ); fann_set_sarprop_temperature(ann,15000.0f); //fann_randomize_weights ( ann, -((rand()%10)*0.1f), ((rand()%10)*0.1f) ); fann_init_weights(ann,train_data); got_inc=0; prev_epoch_mse=1; // epochs=0; unsigned last_best_perc_epoch=0; unsigned last_sync_epoch=0; unsigned last_ftest_secs=0; last_sync_epoch=0; last_best_perc_epoch=0; if (good_ann) fann_destroy(good_ann); good_ann=fann_copy(ann); unlink(histfile); for (u=0;u<1000;u++) { fflush(NULL); train_mse=fann_train_epoch(ann, train_data); if (jitter_train) apply_jjit(train_data,cln_train_data); if (time(NULL)-last_ftest_secs>=1) { //printf("\r\n%5u %9.6f %5.2f ",epochs,train_mse,test_perc); //printf(" %4.2f",test_perc); printf("."); last_ftest_secs=time(NULL); } ftest_data(); plot(epochs,train_mse,test_mse); /* if (epochs>10&&((int)test_perc==43||(int)test_perc==57)) { printf(" [excluded %.2f] ",test_perc); break; } else { } */ //printf("excluded %f ",test_perc); double prev_test_perc; // if (prev_epoch_mse==best_perc) // printf("o"); if ((int)test_perc>(int)train_perc&&epochs-last_stat_epoch>10) { fann_destroy(good_ann); good_ann=fann_copy(ann); if (test_perc!=prev_test_perc) printf("%.2f [%f]",test_perc,train_mse); //printf(" sync[%4.2f]",test_perc); last_stat_epoch=epochs; } else if (epochs-last_sync_epoch>111500) { last_sync_epoch=epochs; } if (epochs>210&&test_perc>best_perc) { // u--; // fann_destroy(good_ann); // good_ann=fann_copy(ann); printf(" [saved best %.0f] ",test_perc); last_stat_epoch=epochs; // printf("%f",test_perc); // fann_destroy(ann); // ann=fann_copy(good_ann); fann_save(ann,"mutate-best.net"); best_perc=test_perc; printf(" %6.2f [%f]",test_perc,train_mse); last_best_perc_epoch=epochs; } else if (epochs>11100&&((int)test_perc<=63||(int)test_perc==(int)prev_test_perc)) { //best_perc=test_perc; // printf("x"); // printf("."); //printf("\r%6.8f",train_mse); // printf("done\r\n"); break; } static unsigned last_restore_epoch=0; if (epochs>100&&test_mse-train_mse>=0.25f&&epochs-last_restore_epoch>=120) { /* fann_set_learning_rate ( ann,0.31f+(rand()%90)*0.01f); fann_set_learning_momentum(ann,(rand()%90)*0.01f); printf(" [restored @ %u lr %.2f mm %.2f]",epochs,fann_get_learning_rate(ann), fann_get_learning_momentum(ann)); fann_destroy(ann); ann=fann_copy(good_ann); last_stat_epoch=epochs; last_restore_epoch=epochs; */ double rdec,rinc; rdec=0.0101f+((rand()%100)*0.00001f); if (!rdec) rdec=0.01f; rinc=1.0001f+((rand()%90)*0.00001f); if (!rinc) rinc=1.1f; static double prev_test_epoch_mse; // rinc+=diff_mse*0.000001f; // fann_set_rprop_increase_factor(ann,rinc ); // fann_set_rprop_decrease_factor(ann, rdec); } else if (test_mse-train_mse<=0.1f) { fann_destroy(good_ann); good_ann=fann_copy(ann); // printf("s"); } else { fann_set_sarprop_temperature(ann,fann_get_sarprop_temperature(ann)-0.0001f); } static unsigned last_train_change_epoch=0; if (test_mse>=train_mse&&epochs-last_train_change_epoch>=100) { last_train_change_epoch=epochs; //fann_set_training_algorithm(ann,FANN_TRAIN_SARPROP); jitter_train=0; } else { //fann_set_training_algorithm(ann,FANN_TRAIN_RPROP); jitter_train=0; } got_inc=test_perc-prev_epoch_mse; prev_epoch_mse=test_perc; prev_test_perc=test_perc; epochs++; if (epochs-last_best_perc_epoch>511500) { printf(" failed"); break; } if (epochs>2200&&(int)train_perc<40) { printf("skip 1\r\n"); break; } if ((int)test_perc>=80) { printf("\r\ngot it %f\r\n",test_perc); fann_save(ann,"good.net"); exit(0); } // printf("\n%6u ",epochs); } printf(" %6.2f inc: %.2f",test_perc,got_inc); // printf("%6.2f %6.2f",train_perc,test_perc); fann_destroy ( ann ); } fann_destroy_train ( train_data ); fann_destroy_train ( test_data ); fann_destroy ( ann ); return 0; }
int main(int argc, char *argv[]) { struct fann_train_data *train, *test, *all; unsigned int i, j; unsigned int length, half_length; if(argc == 2) { train = fann_read_train_from_file(argv[1]); fann_shuffle_train_data(train); fann_scale_train_data(train, 0, 1); fann_save_train(train, argv[1]); return 0; } else if(argc == 3) { train = fann_read_train_from_file(argv[1]); test = fann_read_train_from_file(argv[2]); all = fann_merge_train_data(train, test); fann_shuffle_train_data(all); for(i = 0; i < train->num_data; i++) { for(j = 0; j < train->num_input; j++) { train->input[i][j] = all->input[i][j]; } for(j = 0; j < train->num_output; j++) { train->output[i][j] = all->output[i][j]; } } for(i = 0; i < test->num_data; i++) { for(j = 0; j < test->num_input; j++) { test->input[i][j] = all->input[i + train->num_data][j]; } for(j = 0; j < test->num_output; j++) { test->output[i][j] = all->output[i + train->num_data][j]; } } fann_save_train(train, argv[1]); fann_save_train(test, argv[2]); } else if(argc == 4) { all = fann_read_train_from_file(argv[1]); fann_shuffle_train_data(all); fann_scale_train_data(all, 0, 1); length = fann_length_train_data(all); half_length = length/2; train = fann_subset_train_data(all, 0, half_length); test = fann_subset_train_data(all, half_length, length-half_length); fann_save_train(train, argv[2]); fann_save_train(test, argv[3]); } else { printf("usage: %s train_file\n", argv[0]); printf("will shuffle the data in the file.\n"); printf("usage: %s train_file test_file\n", argv[0]); printf("will shuffle the data in the two files and save the new data back to them.\n"); printf("usage: %s input_file train_file test_file\n", argv[0]); printf("will shuffle the data in the input_file, and split it in two files and save the new data back to them.\n\n"); return -1; } return 0; }