How to use the networkml.utils.training_utils.get_true_label function in networkml

self.logger.info('Getting pcaps')
        pcaps = get_pcap_paths(data_dir)
        if not pcaps:
            self.logger.error(
                'No pcaps were found in data directory; exiting.')
            return

        # Evaluate the model on each pcap
        file_size = 0
        file_num = 0
        time_slices = 0
        self.logger.info('processing pcaps')
        tick = time.clock()
        for pcap in pcaps:
            # Get the true label
            name, label = get_true_label(pcap, label_assignments)
            single_result = {}
            single_result['label'] = label
            self.logger.info('Reading ' + name + ' as ' + label)
            # Get the internal representations
            representations, _, _, p, _, _ = self.model.get_representation(
                pcap, mean=False)
            if representations is not None:
                file_size += os.path.getsize(pcap)
                file_num += 1
                length = representations.shape[0]
                time_slices += length
                single_result['aggregate'] = p
                individual_dict = {}
                # Classify each slice
                self.logger.info('Computing classifications by slice')
                for i in range(length):

self.logger.info('Getting pcaps')
        pcaps = get_pcap_paths(data_dir)
        if not pcaps:
            self.logger.error(
                'No pcaps were found in data directory; exiting.')
            return

        # Evaluate the model on each pcap
        file_size = 0
        file_num = 0
        time_slices = 0
        self.logger.info('processing pcaps')
        tick = time.clock()
        for pcap in pcaps:
            # Get the true label
            name, label = get_true_label(pcap, label_assignments)
            single_result = {}
            single_result['label'] = label
            self.logger.info('Reading ' + name + ' as ' + label)
            # Get the internal representations
            representations, _, _, p, _, _ = self.model.get_representation(
                pcap, mean=False)
            if representations is not None:
                file_size += os.path.getsize(pcap)
                file_num += 1
                length = representations.shape[0]
                time_slices += length
                single_result['aggregate'] = p
                individual_dict = {}
                # Classify each slice
                self.logger.info('Computing classifications by slice')
                for i in range(length):