break end_time = timeit.default_timer() print( ( 'Optimization complete with best validation score of %f %%, ' 'obtained at iteration %i, ' 'with test performance %f %%' ) % (best_validation_loss * 100., best_iter + 1, test_score * 100.) ) print >> sys.stderr, ('The fine tuning code for file ' + os.path.split(__file__)[1] + ' ran for %.2fm' % ((end_time - start_time) / 60.)) if __name__ == '__main__': sup_learn_data = SupLearningData() num_entries, num_input_fields, num_output_fields, input_matrix, output_matrix = sup_learn_data.read_fann_data('datasets/fann/mushroom.train') X_train = numpy.array(input_matrix) y_train = numpy.array(output_matrix) num_entries, num_input_fields, num_output_fields, input_matrix, output_matrix = sup_learn_data.read_fann_data('datasets/fann/mushroom.test') X_val = numpy.array(input_matrix) y_val = numpy.array(output_matrix) datasets = [(X_train, y_train), (X_val, y_val)] test_DBN(datasets=datasets, n_ins=num_input_fields, n_outs=num_output_fields, hidden_layers_sizes=[32, 32, 32])
test_sup_learn_data = SupLearningData() try: exit_code = 1 if args.cmd == 'train': # call the do_this class method if (args.input_data_file_format == 'fann'): """ Test with FANN's building data set, 14 inputs and 3 outputs """ # fann_training_data = 'datasets/fann/building.train' # fann_test_data = 'datasets/fann/building.test' fann_training_data = 'datasets/fann/mushroom.train' fann_test_data = 'datasets/fann/mushroom.test' sup_learn_data = SupLearningData() num_entries, num_input_fields, num_output_fields, input_matrix, output_matrix = sup_learn_data.read_fann_data(fann_training_data) log.info('input_matrix has %d rows and %d cols', len(input_matrix), len(input_matrix[0])) log.info('output_matrix has %d rows and %d cols', len(output_matrix), len(output_matrix[0])) X_train = np.array(input_matrix) y_train = np.array(output_matrix) num_entries, num_input_fields, num_output_fields, input_matrix, output_matrix = sup_learn_data.read_fann_data(fann_test_data) X_val = np.array(input_matrix) y_val = np.array(output_matrix) data = [(X_train, y_train), (X_val, y_val)] do_mlp(dataset=data, n_hidden=[12, 12, 6], mean_loss_threshold=0.001, batch_size=1) elif (args.input_data_file_format == 'jsonz'): """ Test with image data """ jsonz_training_data = '/home/hemkenhg/workspace/theano/examples/image_data/enlarge_center_2x-8-1k-train-a.jsonz' jsonz_test_data = '/home/hemkenhg/workspace/theano/examples/image_data/enlarge_center_2x-8-1k-test-a.jsonz'