if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("-l", "--linguistic_model", type=str, required=True) parser.add_argument("-a", "--acoustic_model", type=str, required=True) args = parser.parse_args() assert isfile( args.acoustic_model), "acoustic_model weights file does not exist" assert isfile(args.acoustic_model.replace( ".torch", ".json")), "acoustic_model config file does not exist" assert isfile( args.linguistic_model), "linguistic_model weights file does not exist" assert isfile(args.linguistic_model.replace( ".torch", ".json")), "linguistic_model config file does not exist" test_features_acoustic, test_labels_acoustic, val_features_acoustic, val_labels_acoustic, _, _ = load_spectrogram_dataset( ) test_iterator_acoustic = BatchIterator(test_features_acoustic, test_labels_acoustic, 100) test_features_linguistic, test_labels_linguistic, val_features_linguistic, val_labels_linguistic, _, _ = load_linguistic_dataset( ) test_iterator_linguistic = BatchIterator(test_features_linguistic, test_labels_linguistic, 100) val_iterator_acoustic = BatchIterator(val_features_acoustic, val_labels_acoustic, 100) val_iterator_linguistic = BatchIterator(val_features_linguistic, val_labels_linguistic, 100) assert np.array_equal( test_labels_acoustic, test_labels_linguistic ), "Labels for acoustic and linguistic datasets are not the same!" """Choosing hardware"""
parser.add_argument("-m", "--model_type", type=str, default="linguistic") args = parser.parse_args() if args.model_type == "linguistic": cfg = LinguisticConfig() test_features, test_labels, val_features, val_labels, train_features, train_labels = load_linguistic_dataset( ) model = RNN(cfg) elif args.model_type == "acoustic-lld": cfg = AcousticLLDConfig() test_features, test_labels, val_features, val_labels, train_features, train_labels = load_acoustic_features_dataset( ) model = RNN(cfg) elif args.model_type == "acoustic-spectrogram": cfg = AcousticSpectrogramConfig() test_features, test_labels, val_features, val_labels, train_features, train_labels = load_spectrogram_dataset( ) model = CNN(cfg) else: raise Exception( "model_type parameter has to be one of [linguistic|acoustic-lld|acoustic-spectrogram]" ) print( "Subsets sizes: test_features:{}, test_labels:{}, val_features:{}, val_labels:{}, train_features:{}, train_labels:{}" .format(test_features.shape[0], test_labels.shape[0], val_features.shape[0], val_labels.shape[0], train_features.shape[0], train_labels.shape[0])) """Running training""" run_training(model, cfg, test_features, test_labels, train_features, train_labels, val_features, val_labels)