See the list of pretrained models, call:
nemo_nlp.huggingface.BERT.list_pretrained_models()
"""
if args.bert_checkpoint and args.bert_config:
pretrained_bert_model = nemo_nlp.huggingface.BERT(
config_filename=args.bert_config, factory=nf)
pretrained_bert_model.restore_from(args.bert_checkpoint)
else:
pretrained_bert_model = nemo_nlp.huggingface.BERT(
pretrained_model_name=args.pretrained_bert_model, factory=nf)
hidden_size = pretrained_bert_model.local_parameters["hidden_size"]
data_desc = JointIntentSlotDataDesc(args.data_dir,
args.do_lower_case,
args.dataset_name,
args.none_slot_label,
args.pad_label)
# Create sentence classification loss on top
classifier = nemo_nlp.JointIntentSlotClassifier(
hidden_size=hidden_size,
num_intents=data_desc.num_intents,
num_slots=data_desc.num_slots,
dropout=args.fc_dropout)
if args.class_balancing == 'weighted_loss':
# Using weighted loss will enable weighted loss for both intents and slots
# Use the intent_loss_weight hyperparameter to adjust intent loss to
# prevent overfitting or underfitting.
loss_fn = nemo_nlp.JointIntentSlotLoss(
raise ValueError(f'Data not found at {args.data_dir}')
nf = nemo.core.NeuralModuleFactory(backend=nemo.core.Backend.PyTorch,
local_rank=args.local_rank,
optimization_level=args.amp_opt_level,
log_dir=None)
""" Load the pretrained BERT parameters
See the list of pretrained models, call:
nemo_nlp.huggingface.BERT.list_pretrained_models()
"""
pretrained_bert_model = nemo_nlp.huggingface.BERT(
pretrained_model_name=args.pretrained_bert_model)
hidden_size = pretrained_bert_model.local_parameters["hidden_size"]
tokenizer = BertTokenizer.from_pretrained(args.pretrained_bert_model)
data_desc = JointIntentSlotDataDesc(args.data_dir, args.do_lower_case,
args.dataset_name)
# Evaluation pipeline
nf.logger.info("Loading eval data...")
data_layer = nemo_nlp.BertJointIntentSlotDataLayer(
input_file=f'{data_desc.data_dir}/{args.eval_file_prefix}.tsv',
slot_file=f'{data_desc.data_dir}/{args.eval_file_prefix}_slots.tsv',
pad_label=data_desc.pad_label,
tokenizer=tokenizer,
max_seq_length=args.max_seq_length,
shuffle=False,
batch_size=args.batch_size,
num_workers=0,
local_rank=args.local_rank)
classifier = nemo_nlp.JointIntentSlotClassifier(