def __init__(self, idim, odim, args, ignore_id=-1):
"""Construct an E2E object.
:param int idim: dimension of inputs
:param int odim: dimension of outputs
:param Namespace args: argument Namespace containing options
"""
torch.nn.Module.__init__(self)
# fill missing arguments for compatibility
args = fill_missing_args(args, self.add_arguments)
if args.transformer_attn_dropout_rate is None:
args.transformer_attn_dropout_rate = args.dropout_rate
self.encoder = Encoder(
idim=idim,
selfattention_layer_type=args.
transformer_encoder_selfattn_layer_type,
attention_dim=args.adim,
attention_heads=args.aheads,
conv_wshare=args.wshare,
conv_kernel_length=args.ldconv_encoder_kernel_length,
conv_usebias=args.ldconv_usebias,
linear_units=args.eunits,
num_blocks=args.elayers,
input_layer="embed",
dropout_rate=args.dropout_rate,
positional_dropout_rate=args.dropout_rate,
attention_dropout_rate=args.transformer_attn_dropout_rate,
)
self.decoder = Decoder(
odim=odim,
selfattention_layer_type=args.
transformer_decoder_selfattn_layer_type,
attention_dim=args.adim,
attention_heads=args.aheads,
conv_wshare=args.wshare,
conv_kernel_length=args.ldconv_decoder_kernel_length,
conv_usebias=args.ldconv_usebias,
linear_units=args.dunits,
num_blocks=args.dlayers,
dropout_rate=args.dropout_rate,
positional_dropout_rate=args.dropout_rate,
self_attention_dropout_rate=args.transformer_attn_dropout_rate,
src_attention_dropout_rate=args.transformer_attn_dropout_rate,
)
self.pad = 0 # use <blank> for padding
self.sos = odim - 1
self.eos = odim - 1
self.odim = odim
self.ignore_id = ignore_id
self.subsample = get_subsample(args, mode="mt", arch="transformer")
self.reporter = Reporter()
# tie source and target emeddings
if args.tie_src_tgt_embedding:
if idim != odim:
raise ValueError(
"When using tie_src_tgt_embedding, idim and odim must be equal."
)
self.encoder.embed[0].weight = self.decoder.embed[0].weight
# tie emeddings and the classfier
if args.tie_classifier:
self.decoder.output_layer.weight = self.decoder.embed[0].weight
self.criterion = LabelSmoothingLoss(
self.odim,
self.ignore_id,
args.lsm_weight,
args.transformer_length_normalized_loss,
)
self.normalize_length = args.transformer_length_normalized_loss # for PPL
self.reset_parameters(args)
self.adim = args.adim
self.error_calculator = ErrorCalculator(args.char_list, args.sym_space,
args.sym_blank,
args.report_bleu)
self.rnnlm = None
# multilingual MT related
self.multilingual = args.multilingual
def __init__(self, idim, odim, args, ignore_id=-1):
"""Construct an E2E object.
:param int idim: dimension of inputs
:param int odim: dimension of outputs
:param Namespace args: argument Namespace containing options
"""
torch.nn.Module.__init__(self)
if args.transformer_attn_dropout_rate is None:
args.transformer_attn_dropout_rate = args.dropout_rate
self.encoder = Encoder(
idim=idim,
attention_dim=args.adim,
attention_heads=args.aheads,
linear_units=args.eunits,
num_blocks=args.elayers,
input_layer='embed',
dropout_rate=args.dropout_rate,
positional_dropout_rate=args.dropout_rate,
attention_dropout_rate=args.transformer_attn_dropout_rate,
)
self.decoder = Decoder(
odim=odim,
attention_dim=args.adim,
attention_heads=args.aheads,
linear_units=args.dunits,
num_blocks=args.dlayers,
dropout_rate=args.dropout_rate,
positional_dropout_rate=args.dropout_rate,
self_attention_dropout_rate=args.transformer_attn_dropout_rate,
src_attention_dropout_rate=args.transformer_attn_dropout_rate,
)
self.pad = 0
self.sos = odim - 1
self.eos = odim - 1
self.odim = odim
self.ignore_id = ignore_id
self.subsample = get_subsample(args, mode='mt', arch='transformer')
self.reporter = Reporter()
# tie source and target emeddings
if args.tie_src_tgt_embedding:
if idim != odim:
raise ValueError(
'When using tie_src_tgt_embedding, idim and odim must be equal.'
)
self.encoder.embed[0].weight = self.decoder.embed[0].weight
# tie emeddings and the classfier
if args.tie_classifier:
self.decoder.output_layer.weight = self.decoder.embed[0].weight
# self.lsm_weight = a
self.criterion = LabelSmoothingLoss(
self.odim, self.ignore_id, args.lsm_weight,
args.transformer_length_normalized_loss)
self.normalize_length = args.transformer_length_normalized_loss # for PPL
# self.verbose = args.verbose
self.reset_parameters(args)
self.adim = args.adim
if args.report_bleu:
from espnet.nets.e2e_mt_common import ErrorCalculator
self.error_calculator = ErrorCalculator(args.char_list,
args.sym_space,
args.report_bleu)
else:
self.error_calculator = None
self.rnnlm = None
# multilingual NMT related
self.multilingual = args.multilingual