combine_strategy=args.combine_strategy,
rnn_bias=True,
device=torch.device(args.device),
num_layers=args.num_layers,
add_projection_layer=False,
)
model = RnnSeqCrfTagger(
rnn2seqencoder=lstm2seqencoder,
encoding_dim=2 * args.hidden_dim if args.bidirectional
and args.combine_strategy == "concat" else args.hidden_dim,
device=torch.device(args.device),
tagging_type="BIOUL",
datasets_manager=data_manager,
)
optimizer = optim.Adam(params=model.parameters(),
lr=args.lr,
weight_decay=args.reg)
train_metric = TokenClassificationAccuracy(datasets_manager=data_manager)
dev_metric = TokenClassificationAccuracy(datasets_manager=data_manager)
test_metric = TokenClassificationAccuracy(datasets_manager=data_manager)
engine = Engine(
model=model,
datasets_manager=data_manager,
optimizer=optimizer,
batch_size=args.bs,
save_dir=args.model_save_dir,
num_epochs=args.epochs,
save_every=args.save_every,
def setup_parscit_inference(seq_dataset_manager, tmpdir_factory):
HIDDEN_DIM = 100
BIDIRECTIONAL = True
COMBINE_STRATEGY = "concat"
dataset_manager = seq_dataset_manager
embedder = WordEmbedder(embedding_type="glove_6B_50")
char_embedder = CharEmbedder(
char_embedding_dimension=10,
hidden_dimension=20,
datasets_manager=dataset_manager,
)
embedder = ConcatEmbedders([embedder, char_embedder])
encoder = Lstm2SeqEncoder(
embedder=embedder,
dropout_value=0.0,
hidden_dim=HIDDEN_DIM,
bidirectional=BIDIRECTIONAL,
combine_strategy=COMBINE_STRATEGY,
rnn_bias=False,
add_projection_layer=False,
)
tagger = RnnSeqCrfTagger(
rnn2seqencoder=encoder,
encoding_dim=2 * HIDDEN_DIM
if BIDIRECTIONAL and COMBINE_STRATEGY == "concat"
else HIDDEN_DIM,
datasets_manager=dataset_manager,
)
train_metric = TokenClassificationAccuracy(datasets_manager=dataset_manager)
dev_metric = TokenClassificationAccuracy(datasets_manager=dataset_manager)
test_metric = TokenClassificationAccuracy(datasets_manager=dataset_manager)
optimizer = torch.optim.Adam(params=tagger.parameters())
batch_size = 1
save_dir = tmpdir_factory.mktemp("experiment_1")
num_epochs = 1
save_every = 1
log_train_metrics_every = 10
engine = Engine(
model=tagger,
datasets_manager=dataset_manager,
optimizer=optimizer,
batch_size=batch_size,
save_dir=save_dir,
num_epochs=num_epochs,
save_every=save_every,
log_train_metrics_every=log_train_metrics_every,
train_metric=train_metric,
validation_metric=dev_metric,
test_metric=test_metric,
track_for_best="macro_fscore",
)
engine.run()
model_filepath = pathlib.Path(save_dir).joinpath("best_model.pt")
inference_client = SequenceLabellingInference(
model=tagger, model_filepath=model_filepath, datasets_manager=dataset_manager
)
return inference_client
combine_strategy=args.combine_strategy,
rnn_bias=True,
device=args.device,
num_layers=args.num_layers,
add_projection_layer=args.add_projection_layer,
)
model = RnnSeqCrfTagger(
rnn2seqencoder=lstm2seqencoder,
encoding_dim=2 * args.hidden_dim,
device=args.device,
tagging_type="BIOUL",
datasets_manager=data_manager,
include_start_end_trainsitions=False,
)
optimizer = optim.Adam(params=model.parameters(), lr=args.lr)
train_metric = ConLL2003Metrics(datasets_manager=data_manager)
dev_metric = ConLL2003Metrics(datasets_manager=data_manager)
test_metric = ConLL2003Metrics(datasets_manager=data_manager)
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(
optimizer=optimizer,
factor=0.1,
mode="max",
patience=25,
verbose=True,
threshold=1e-3,
)
engine = Engine(
combine_strategy=args.combine_strategy,
rnn_bias=True,
device=torch.device(args.device),
num_layers=args.num_layers,
)
model = RnnSeqCrfTagger(
rnn2seqencoder=lstm2seqencoder,
encoding_dim=2 * args.hidden_dim
if args.bidirectional and args.combine_strategy == "concat"
else args.hidden_dim,
device=torch.device(args.device),
tagging_type="BIOUL",
datasets_manager=data_manager,
)
optimizer = optim.Adam(params=model.parameters(), lr=args.lr, weight_decay=args.reg)
train_metric = TokenClassificationAccuracy(datasets_manager=data_manager)
dev_metric = TokenClassificationAccuracy(datasets_manager=data_manager)
test_metric = TokenClassificationAccuracy(datasets_manager=data_manager)
engine = Engine(
model=model,
datasets_manager=data_manager,
optimizer=optimizer,
batch_size=args.bs,
save_dir=args.model_save_dir,
num_epochs=args.epochs,
save_every=args.save_every,
log_train_metrics_every=args.log_train_metrics_every,
track_for_best="macro_fscore",