def load_dataset_wavegan(): """Load WaveGAN's dataset. The loaded dataset consists of: - original data (dataset_blob, train_data, train_label), - encoded data from a pretrained model (train_mu, train_sigma), and - index grouped by label (index_grouped_by_label). Some of these attributes are not avaiable (set as None) but are left here to keep everything aligned with returned value of `load_dataset`. Returns: An tuple of abovementioned components in the dataset. """ latent_dir = os.path.expanduser(FLAGS.wavegan_latent_dir) path_train = os.path.join(latent_dir, 'data_train.npz') train = np.load(path_train) train_z = train['z'] train_label = train['label'] index_grouped_by_label = common.get_index_grouped_by_label(train_label) dataset_blob, train_data = None, None train_mu, train_sigma = train_z, None return (dataset_blob, train_data, train_label, train_mu, train_sigma, index_grouped_by_label)
def load_dataset_wavegan(): """Load WaveGAN's dataset. The loaded dataset consists of: - original data (dataset_blob, train_data, train_label), - encoded data from a pretrained model (train_mu, train_sigma), and - index grouped by label (index_grouped_by_label). Some of these attributes are not avaiable (set as None) but are left here to keep everything aligned with returned value of `load_dataset`. Returns: An tuple of abovementioned components in the dataset. """ latent_dir = os.path.expanduser(FLAGS.wavegan_latent_dir) path_train = os.path.join(latent_dir, 'data_train.npz') train = np.load(path_train) train_z = train['z'] train_label = train['label'] index_grouped_by_label = common.get_index_grouped_by_label(train_label) dataset_blob, train_data = None, None train_mu, train_sigma = train_z, None return (dataset_blob, train_data, train_label, train_mu, train_sigma, index_grouped_by_label)
def load_dataset(config_name, exp_uid): """Load a dataset from a config's name. The loaded dataset consists of: - original data (dataset_blob, train_data, train_label), - encoded data from a pretrained model (train_mu, train_sigma), and - index grouped by label (index_grouped_by_label). Args: config_name: A string indicating the name of config to parameterize the model that associates with the dataset. exp_uid: A string representing the unique id of experiment to be used in model that associates with the dataset. Returns: An tuple of abovementioned components in the dataset. """ config = load_config(config_name) if config_is_wavegan(config): return load_dataset_wavegan() model_uid = common.get_model_uid(config_name, exp_uid) dataset = common.load_dataset(config) train_data = dataset.train_data attr_train = dataset.attr_train path_train = os.path.join(dataset.basepath, 'encoded', model_uid, 'encoded_train_data.npz') train = np.load(path_train) train_mu = train['mu'] train_sigma = train['sigma'] train_label = np.argmax(attr_train, axis=-1) # from one-hot to label index_grouped_by_label = common.get_index_grouped_by_label(train_label) tf.logging.info('index_grouped_by_label size: %s', [len(_) for _ in index_grouped_by_label]) tf.logging.info('train loaded from %s', path_train) tf.logging.info('train shapes: mu = %s, sigma = %s', train_mu.shape, train_sigma.shape) dataset_blob = dataset return (dataset_blob, train_data, train_label, train_mu, train_sigma, index_grouped_by_label)
def load_dataset(config_name, exp_uid): """Load a dataset from a config's name. The loaded dataset consists of: - original data (dataset_blob, train_data, train_label), - encoded data from a pretrained model (train_mu, train_sigma), and - index grouped by label (index_grouped_by_label). Args: config_name: A string indicating the name of config to parameterize the model that associates with the dataset. exp_uid: A string representing the unique id of experiment to be used in model that associates with the dataset. Returns: An tuple of abovementioned components in the dataset. """ config = load_config(config_name) if config_is_wavegan(config): return load_dataset_wavegan() model_uid = common.get_model_uid(config_name, exp_uid) dataset = common.load_dataset(config) train_data = dataset.train_data attr_train = dataset.attr_train path_train = os.path.join(dataset.basepath, 'encoded', model_uid, 'encoded_train_data.npz') train = np.load(path_train) train_mu = train['mu'] train_sigma = train['sigma'] train_label = np.argmax(attr_train, axis=-1) # from one-hot to label index_grouped_by_label = common.get_index_grouped_by_label(train_label) tf.logging.info('index_grouped_by_label size: %s', [len(_) for _ in index_grouped_by_label]) tf.logging.info('train loaded from %s', path_train) tf.logging.info('train shapes: mu = %s, sigma = %s', train_mu.shape, train_sigma.shape) dataset_blob = dataset return (dataset_blob, train_data, train_label, train_mu, train_sigma, index_grouped_by_label)