Python utils.print_embed_overlap方法代码示例

# 需要导入模块: from fairseq import utils [as 别名]
# 或者: from fairseq.utils import print_embed_overlap [as 别名]
def build_model(cls, args, task):
        """Build a new model instance."""
        # make sure that all args are properly defaulted (in case there are any new ones)
        base_architecture(args)

        encoder_embed_dict = None
        if args.encoder_embed_path:
            encoder_embed_dict = utils.parse_embedding(args.encoder_embed_path)
            utils.print_embed_overlap(encoder_embed_dict, task.source_dictionary)

        decoder_embed_dict = None
        if args.decoder_embed_path:
            decoder_embed_dict = utils.parse_embedding(args.decoder_embed_path)
            utils.print_embed_overlap(decoder_embed_dict, task.target_dictionary)

        encoder = FConvEncoder(
            dictionary=task.source_dictionary,
            embed_dim=args.encoder_embed_dim,
            embed_dict=encoder_embed_dict,
            convolutions=eval(args.encoder_layers),
            dropout=args.dropout,
            max_positions=args.max_source_positions,
            normalization_constant=args.normalization_constant,
        )
        decoder = FConvDecoder(
            dictionary=task.target_dictionary,
            embed_dim=args.decoder_embed_dim,
            embed_dict=decoder_embed_dict,
            convolutions=eval(args.decoder_layers),
            out_embed_dim=args.decoder_out_embed_dim,
            attention=eval(args.decoder_attention),
            dropout=args.dropout,
            max_positions=args.max_target_positions,
            share_embed=args.share_input_output_embed,
            normalization_constant=args.normalization_constant,
        )
        return FConvModel(encoder, decoder) 

# 需要导入模块: from fairseq import utils [as 别名]
# 或者: from fairseq.utils import print_embed_overlap [as 别名]
def build_model(cls, args, task):
        """Build a new model instance."""
        # make sure that all args are properly defaulted (in case there are any new ones)
        base_architecture(args)

        encoder_embed_dict = None
        if args.encoder_embed_path:
            encoder_embed_dict = utils.parse_embedding(args.encoder_embed_path)
            utils.print_embed_overlap(encoder_embed_dict, task.source_dictionary)

        decoder_embed_dict = None
        if args.decoder_embed_path:
            decoder_embed_dict = utils.parse_embedding(args.decoder_embed_path)
            utils.print_embed_overlap(decoder_embed_dict, task.target_dictionary)

        encoder = FConvCustomEncoder(
            dictionary=task.source_dictionary,
            embed_dim=args.encoder_embed_dim,
            embed_dict=encoder_embed_dict,
            convolutions=eval(args.encoder_layers),
            dropout=args.dropout,
            max_positions=args.max_source_positions,
            normalization_constant=args.normalization_constant,
            token_dropout=args.source_token_dropout,
        )
        decoder = FConvCustomDecoder(
            dictionary=task.target_dictionary,
            embed_dim=args.decoder_embed_dim,
            embed_dict=decoder_embed_dict,
            convolutions=eval(args.decoder_layers),
            out_embed_dim=args.decoder_out_embed_dim,
            attention=eval(args.decoder_attention),
            dropout=args.dropout,
            max_positions=args.max_target_positions,
            share_embed=args.share_input_output_embed,
            normalization_constant=args.normalization_constant,
        )
        return FConvCustomModel(encoder, decoder) 

# 需要导入模块: from fairseq import utils [as 别名]
# 或者: from fairseq.utils import print_embed_overlap [as 别名]
def build_model(cls, args, task):
        """Build a new model instance."""
        # make sure that all args are properly defaulted (in case there are any new ones)
        base_architecture(args)

        encoder_embed_dict = None
        if args.encoder_embed_path:
            encoder_embed_dict = utils.parse_embedding(args.encoder_embed_path)
            utils.print_embed_overlap(encoder_embed_dict, task.source_dictionary)

        decoder_embed_dict = None
        if args.decoder_embed_path:
            decoder_embed_dict = utils.parse_embedding(args.decoder_embed_path)
            utils.print_embed_overlap(decoder_embed_dict, task.target_dictionary)

        encoder = FConvEncoder(
            dictionary=task.source_dictionary,
            embed_dim=args.encoder_embed_dim,
            embed_dict=encoder_embed_dict,
            convolutions=eval(args.encoder_layers),
            dropout=args.dropout,
            max_positions=args.max_source_positions,
        )
        decoder = FConvDecoder(
            dictionary=task.target_dictionary,
            embed_dim=args.decoder_embed_dim,
            embed_dict=decoder_embed_dict,
            convolutions=eval(args.decoder_layers),
            out_embed_dim=args.decoder_out_embed_dim,
            attention=eval(args.decoder_attention),
            dropout=args.dropout,
            max_positions=args.max_target_positions,
            share_embed=args.share_input_output_embed,
        )
        return FConvModel(encoder, decoder) 

# 需要导入模块: from fairseq import utils [as 别名]
# 或者: from fairseq.utils import print_embed_overlap [as 别名]
def build_model(cls, args, task):
        """Build a new model instance."""
        # make sure that all args are properly defaulted (in case there are any new ones)
        base_architecture(args)

        encoder_embed_dict = None
        if args.encoder_embed_path:
            encoder_embed_dict = utils.parse_embedding(args.encoder_embed_path)
            utils.print_embed_overlap(encoder_embed_dict, task.source_dictionary)

        auxencoder_embed_dict = None
        if args.auxencoder_embed_path:
            auxencoder_embed_dict = utils.parse_embedding(args.auxencoder_embed_path)
            utils.print_embed_overlap(auxencoder_embed_dict, task.context_dictionary)

        decoder_embed_dict = None
        if args.decoder_embed_path:
            decoder_embed_dict = utils.parse_embedding(args.decoder_embed_path)
            utils.print_embed_overlap(decoder_embed_dict, task.target_dictionary)

        auxencoder = FConvCustomEncoder(
            dictionary=task.context_dictionary,
            embed_dim=args.auxencoder_embed_dim,
            embed_dict=auxencoder_embed_dict,
            convolutions=eval(args.auxencoder_layers),
            dropout=args.dropout,
            max_positions=args.max_context_positions,
            normalization_constant=args.normalization_constant,
        )

        encoder = FConvCustomEncoder(
            dictionary=task.source_dictionary,
            embed_dim=args.encoder_embed_dim,
            embed_dict=encoder_embed_dict,
            convolutions=eval(args.encoder_layers),
            dropout=args.dropout,
            max_positions=args.max_source_positions,
            normalization_constant=args.normalization_constant,
            token_dropout=args.source_token_dropout,
        )
        decoder = FConvCustomDecoder(
            dictionary=task.target_dictionary,
            embed_dim=args.decoder_embed_dim,
            embed_dict=decoder_embed_dict,
            convolutions=eval(args.decoder_layers),
            out_embed_dim=args.decoder_out_embed_dim,
            attention=eval(args.decoder_attention),
            dropout=args.dropout,
            max_positions=args.max_target_positions,
            share_embed=args.share_input_output_embed,
            normalization_constant=args.normalization_constant,
        )
        return FConvDualEncoderModel(auxencoder, encoder, decoder) 

# 需要导入模块: from fairseq import utils [as 别名]
# 或者: from fairseq.utils import print_embed_overlap [as 别名]
def build_model(cls, args, task):
        """Build a new model instance."""
        # make sure that all args are properly defaulted (in case there are any new ones)
        base_architecture(args)

        def load_pretrained_embedding_from_file(embed_path, dictionary, embed_dim):
            num_embeddings = len(dictionary)
            padding_idx = dictionary.pad()
            embed_tokens = Embedding(num_embeddings, embed_dim, padding_idx)
            embed_dict = utils.parse_embedding(embed_path)
            utils.print_embed_overlap(embed_dict, dictionary)
            return utils.load_embedding(embed_dict, dictionary, embed_tokens)

        pretrained_encoder_embed = None
        if args.encoder_embed_path:
            pretrained_encoder_embed = load_pretrained_embedding_from_file(
                args.encoder_embed_path, task.source_dictionary, args.encoder_embed_dim)
        pretrained_decoder_embed = None
        if args.decoder_embed_path:
            pretrained_decoder_embed = load_pretrained_embedding_from_file(
                args.decoder_embed_path, task.target_dictionary, args.decoder_embed_dim)

        encoder = LSTMEncoder(
            dictionary=task.source_dictionary,
            embed_dim=args.encoder_embed_dim,
            hidden_size=args.encoder_hidden_size,
            num_layers=args.encoder_layers,
            dropout_in=args.encoder_dropout_in,
            dropout_out=args.encoder_dropout_out,
            bidirectional=args.encoder_bidirectional,
            pretrained_embed=pretrained_encoder_embed,
        )
        decoder = LSTMDecoder(
            dictionary=task.target_dictionary,
            embed_dim=args.decoder_embed_dim,
            hidden_size=args.decoder_hidden_size,
            out_embed_dim=args.decoder_out_embed_dim,
            num_layers=args.decoder_layers,
            dropout_in=args.decoder_dropout_in,
            dropout_out=args.decoder_dropout_out,
            attention=options.eval_bool(args.decoder_attention),
            encoder_embed_dim=args.encoder_embed_dim,
            encoder_output_units=encoder.output_units,
            pretrained_embed=pretrained_decoder_embed,
        )
        return cls(encoder, decoder) 

# 需要导入模块: from fairseq import utils [as 别名]
# 或者: from fairseq.utils import print_embed_overlap [as 别名]
def build_model(cls, args, task):
        """Build a new model instance."""

        # make sure all arguments are present in older models
        base_architecture(args)

        if getattr(args, 'max_target_positions', None) is not None:
            max_target_positions = args.max_target_positions
        else:
            max_target_positions = getattr(args, 'tokens_per_sample', DEFAULT_MAX_TARGET_POSITIONS)

        def load_pretrained_embedding_from_file(embed_path, dictionary, embed_dim):
            num_embeddings = len(dictionary)
            padding_idx = dictionary.pad()
            embed_tokens = Embedding(num_embeddings, embed_dim, padding_idx)
            embed_dict = utils.parse_embedding(embed_path)
            utils.print_embed_overlap(embed_dict, dictionary)
            return utils.load_embedding(embed_dict, dictionary, embed_tokens)

        pretrained_decoder_embed = None
        if args.decoder_embed_path:
            pretrained_decoder_embed = load_pretrained_embedding_from_file(
                args.decoder_embed_path,
                task.target_dictionary,
                args.decoder_embed_dim
            )

        if args.share_decoder_input_output_embed:
            # double check all parameters combinations are valid
            if task.source_dictionary != task.target_dictionary:
                raise ValueError('--share-decoder-input-output-embeddings requires a joint dictionary')

            if args.decoder_embed_dim != args.decoder_out_embed_dim:
                raise ValueError(
                    '--share-decoder-input-output-embeddings requires '
                    '--decoder-embed-dim to match --decoder-out-embed-dim'
                    )

        decoder = LSTMDecoder(
            dictionary=task.dictionary,
            embed_dim=args.decoder_embed_dim,
            hidden_size=args.decoder_hidden_size,
            out_embed_dim=args.decoder_out_embed_dim,
            num_layers=args.decoder_layers,
            dropout_in=args.decoder_dropout_in,
            dropout_out=args.decoder_dropout_out,
            attention=False,  # decoder-only language model doesn't support attention
            encoder_output_units=0,
            pretrained_embed=pretrained_decoder_embed,
            share_input_output_embed=args.share_decoder_input_output_embed,
            adaptive_softmax_cutoff=(
                options.eval_str_list(args.adaptive_softmax_cutoff, type=int)
                if args.criterion == 'adaptive_loss' else None
            ),
            max_target_positions=max_target_positions,
            residuals=args.residuals
        )

        return cls(decoder) 

# 需要导入模块: from fairseq import utils [as 别名]
# 或者: from fairseq.utils import print_embed_overlap [as 别名]
def build_model(cls, args, task):
        """Build a new model instance."""

        # make sure all arguments are present in older models
        base_architecture(args)

        if getattr(args, 'max_target_positions', None) is not None:
            max_target_positions = args.max_target_positions
        else:
            max_target_positions = getattr(args, 'tokens_per_sample', DEFAULT_MAX_TARGET_POSITIONS)

        def load_pretrained_embedding_from_file(embed_path, dictionary, embed_dim):
            num_embeddings = len(dictionary)
            padding_idx = dictionary.pad()
            embed_tokens = Embedding(num_embeddings, embed_dim, padding_idx)
            embed_dict = utils.parse_embedding(embed_path)
            utils.print_embed_overlap(embed_dict, dictionary)
            return utils.load_embedding(embed_dict, dictionary, embed_tokens)

        pretrained_decoder_embed = None
        if args.decoder_embed_path:
            pretrained_decoder_embed = load_pretrained_embedding_from_file(
                args.decoder_embed_path,
                task.target_dictionary,
                args.decoder_embed_dim
            )

        if args.share_decoder_input_output_embed:
            # double check all parameters combinations are valid
            if task.source_dictionary != task.target_dictionary:
                raise ValueError('--share-decoder-input-output-embeddings requires a joint dictionary')

            if args.decoder_embed_dim != args.decoder_out_embed_dim:
                raise ValueError(
                    '--share-decoder-input-output-embeddings requires '
                    '--decoder-embed-dim to match --decoder-out-embed-dim'
                    )

        decoder = LSTMDecoder(
            dictionary=task.dictionary,
            embed_dim=args.decoder_embed_dim,
            hidden_size=args.decoder_hidden_size,
            out_embed_dim=args.decoder_out_embed_dim,
            num_layers=args.decoder_layers,
            dropout_in=args.decoder_dropout_in,
            dropout_out=args.decoder_dropout_out,
            attention=options.eval_bool(args.decoder_attention),
            encoder_output_units=0,
            pretrained_embed=pretrained_decoder_embed,
            share_input_output_embed=args.share_decoder_input_output_embed,
            adaptive_softmax_cutoff=(
                options.eval_str_list(args.adaptive_softmax_cutoff, type=int)
                if args.criterion == 'adaptive_loss' else None
            ),
            max_target_positions=max_target_positions
        )

        return cls(decoder)