def init(config_filename, cmd_line_opts, dataset_config_str): """ :param str config_filename: global config for CRNN :param list[str] cmd_line_opts: options for init_config method :param str dataset_config_str: dataset via init_dataset_via_str() """ rnn.init_better_exchook() rnn.init_thread_join_hack() if config_filename: rnn.init_config(config_filename, cmd_line_opts) rnn.init_log() else: log.initialize(verbosity=[5]) print("Returnn hdf_dump starting up.", file=log.v3) rnn.init_faulthandler() if config_filename: rnn.init_data() rnn.print_task_properties() assert isinstance(rnn.train_data, Dataset) dataset = rnn.train_data else: assert dataset_config_str dataset = init_dataset(dataset_config_str) print("Source dataset:", dataset.len_info(), file=log.v3) return dataset
def init(config_str, verbosity): """ :param str config_str: either filename to config-file, or dict for dataset :param int verbosity: """ rnn.init_better_exchook() rnn.init_thread_join_hack() datasetDict = None configFilename = None if config_str.strip().startswith("{"): print("Using dataset %s." % config_str) datasetDict = eval(config_str.strip()) elif config_str.endswith(".hdf"): datasetDict = {"class": "HDFDataset", "files": [config_str]} print("Using dataset %r." % datasetDict) assert os.path.exists(config_str) else: configFilename = config_str print("Using config file %r." % configFilename) assert os.path.exists(configFilename) rnn.init_config(config_filename=configFilename, default_config={"cache_size": "0"}) global config config = rnn.config config.set("log", None) config.set("log_verbosity", verbosity) if datasetDict: config.set("train", datasetDict) rnn.init_log() print("Returnn dump-dataset starting up.", file=log.v2) rnn.returnn_greeting() rnn.init_faulthandler() rnn.init_config_json_network() rnn.init_data() rnn.print_task_properties()
def init(configFilename, commandLineOptions): rnn.init_better_exchook() rnn.init_thread_join_hack() rnn.init_config(configFilename, commandLineOptions) global config config = rnn.config rnn.init_log() print("CRNN demo-dataset starting up", file=log.v3) rnn.init_faulthandler() rnn.init_config_json_network() rnn.init_data() rnn.print_task_properties()
def test_rnn_initData(): hdf_fn = generate_hdf_from_dummy() from Config import Config config = Config({"cache_size": "0", "train": hdf_fn, "dev": hdf_fn}) import rnn rnn.config = config rnn.init_data() train, dev = rnn.train_data, rnn.dev_data assert train and dev assert isinstance(train, HDFDataset) assert isinstance(dev, HDFDataset) assert train.cache_byte_size_total_limit == dev.cache_byte_size_total_limit == 0 assert train.cache_byte_size_limit_at_start == dev.cache_byte_size_limit_at_start == 0
def init(configFilename=None): rnn.init_better_exchook() rnn.init_thread_join_hack() if configFilename: rnn.init_config(configFilename, command_line_options=[]) rnn.init_log() else: log.initialize() print("Returnn collect-words starting up.", file=log.v3) rnn.init_faulthandler() if configFilename: rnn.init_config_json_network() rnn.init_data() rnn.print_task_properties()