sockeye/train.py [311:353]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            batch_sentences_multiple_of=args.batch_sentences_multiple_of)

        check_condition(all([combine in [C.FACTORS_COMBINE_SUM, C.FACTORS_COMBINE_AVERAGE]
                             for combine in args.source_factors_combine])
                        or len(source_vocabs) == len(args.source_factors_num_embed) + 1,
                        "Data was prepared with %d source factors, but only provided %d source factor dimensions." % (
                            len(source_vocabs), len(args.source_factors_num_embed) + 1))
        check_condition(all([combine in [C.FACTORS_COMBINE_SUM, C.FACTORS_COMBINE_AVERAGE]
                             for combine in args.target_factors_combine])
                        or len(target_vocabs) == len(args.target_factors_num_embed) + 1,
                        "Data was prepared with %d target factors, but only provided %d target factor dimensions." % (
                            len(target_vocabs), len(args.target_factors_num_embed) + 1))

        if resume_training:
            # resuming training. Making sure the vocabs in the model and in the prepared data match up
            model_source_vocabs = vocab.load_source_vocabs(output_folder)
            for i, (v, mv) in enumerate(zip(source_vocabs, model_source_vocabs)):
                utils.check_condition(vocab.are_identical(v, mv),
                                      "Prepared data and resumed model source vocab %d do not match." % i)
            model_target_vocabs = vocab.load_target_vocabs(output_folder)
            for i, (v, mv) in enumerate(zip(target_vocabs, model_target_vocabs)):
                utils.check_condition(vocab.are_identical(v, mv),
                                      "Prepared data and resumed model target vocab %d do not match." % i)

        check_condition(data_config.num_source_factors == len(validation_sources),
                        'Training and validation data must have the same number of source factors,'
                        ' but found %d and %d.' % (
                            data_config.num_source_factors, len(validation_sources)))
        check_condition(data_config.num_target_factors == len(validation_targets),
                        'Training and validation data must have the same number of target factors,'
                        ' but found %d and %d.' % (
                            data_config.num_target_factors, len(validation_targets)))

        return train_iter, validation_iter, data_config, source_vocabs, target_vocabs

    else:
        utils.check_condition(args.prepared_data is None and args.source is not None and args.target is not None,
                              either_raw_or_prepared_error_msg)

        if resume_training:
            # Load the existing vocabs created when starting the training run.
            source_vocabs = vocab.load_source_vocabs(output_folder)
            target_vocabs = vocab.load_target_vocabs(output_folder)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



sockeye/train_pt.py [289:331]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            batch_sentences_multiple_of=args.batch_sentences_multiple_of)

        check_condition(all([combine in [C.FACTORS_COMBINE_SUM, C.FACTORS_COMBINE_AVERAGE]
                             for combine in args.source_factors_combine])
                        or len(source_vocabs) == len(args.source_factors_num_embed) + 1,
                        "Data was prepared with %d source factors, but only provided %d source factor dimensions." % (
                            len(source_vocabs), len(args.source_factors_num_embed) + 1))
        check_condition(all([combine in [C.FACTORS_COMBINE_SUM, C.FACTORS_COMBINE_AVERAGE]
                             for combine in args.target_factors_combine])
                        or len(target_vocabs) == len(args.target_factors_num_embed) + 1,
                        "Data was prepared with %d target factors, but only provided %d target factor dimensions." % (
                            len(target_vocabs), len(args.target_factors_num_embed) + 1))

        if resume_training:
            # resuming training. Making sure the vocabs in the model and in the prepared data match up
            model_source_vocabs = vocab.load_source_vocabs(output_folder)
            for i, (v, mv) in enumerate(zip(source_vocabs, model_source_vocabs)):
                utils.check_condition(vocab.are_identical(v, mv),
                                      "Prepared data and resumed model source vocab %d do not match." % i)
            model_target_vocabs = vocab.load_target_vocabs(output_folder)
            for i, (v, mv) in enumerate(zip(target_vocabs, model_target_vocabs)):
                utils.check_condition(vocab.are_identical(v, mv),
                                      "Prepared data and resumed model target vocab %d do not match." % i)

        check_condition(data_config.num_source_factors == len(validation_sources),
                        'Training and validation data must have the same number of source factors,'
                        ' but found %d and %d.' % (
                            data_config.num_source_factors, len(validation_sources)))
        check_condition(data_config.num_target_factors == len(validation_targets),
                        'Training and validation data must have the same number of target factors,'
                        ' but found %d and %d.' % (
                            data_config.num_target_factors, len(validation_targets)))

        return train_iter, validation_iter, data_config, source_vocabs, target_vocabs

    else:
        utils.check_condition(args.prepared_data is None and args.source is not None and args.target is not None,
                              either_raw_or_prepared_error_msg)

        if resume_training:
            # Load the existing vocabs created when starting the training run.
            source_vocabs = vocab.load_source_vocabs(output_folder)
            target_vocabs = vocab.load_target_vocabs(output_folder)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -