tokenizer=tokenizer,
max_seq_len=args.max_seq_len)
# Construct transfer learning network
# Use "pooled_output" for classification tasks on an entire sentence.
# Use "sequence_output" for token-level output.
pooled_output = outputs["pooled_output"]
# Select fine-tune strategy, setup config and fine-tune
strategy = hub.AdamWeightDecayStrategy(
warmup_proportion=args.warmup_proportion,
weight_decay=args.weight_decay,
learning_rate=args.learning_rate)
# Setup RunConfig for PaddleHub Fine-tune API
config = hub.RunConfig(use_data_parallel=args.use_data_parallel,
use_cuda=args.use_gpu,
num_epoch=args.num_epoch,
batch_size=args.batch_size,
checkpoint_dir=args.checkpoint_dir,
strategy=strategy)
# Define a regression fine-tune task by PaddleHub's API
reg_task = hub.RegressionTask(dataset=dataset,
feature=pooled_output,
config=config)
# Fine-tune and evaluate by PaddleHub's API
# will finish training, evaluation, testing, save model automatically
reg_task.finetune_and_eval()
inputs["segment_ids"].name,
inputs["input_mask"].name,
]
if args.use_taskid:
feed_list.append(inputs["task_ids"].name)
# Select finetune strategy, setup config and finetune
strategy = hub.AdamWeightDecayStrategy(weight_decay=args.weight_decay,
learning_rate=args.learning_rate,
lr_scheduler="linear_decay")
# Setup runing config for PaddleHub Finetune API
config = hub.RunConfig(use_data_parallel=args.use_data_parallel,
use_pyreader=args.use_pyreader,
use_cuda=args.use_gpu,
num_epoch=args.num_epoch,
batch_size=args.batch_size,
checkpoint_dir=args.checkpoint_dir,
strategy=strategy)
# Define a regression finetune task by PaddleHub's API
reg_task = hub.RegressionTask(data_reader=reader,
feature=pooled_output,
feed_list=feed_list,
config=config)
# Finetune and evaluate by PaddleHub's API
# will finish training, evaluation, testing, save model automatically
reg_task.finetune_and_eval()
# Construct transfer learning network
# Use "pooled_output" for classification tasks on an entire sentence.
# Use "sequence_output" for token-level output.
pooled_output = outputs["pooled_output"]
# Setup RunConfig for PaddleHub Fine-tune API
config = hub.RunConfig(use_data_parallel=False,
use_cuda=args.use_gpu,
batch_size=args.batch_size,
checkpoint_dir=args.checkpoint_dir,
strategy=hub.AdamWeightDecayStrategy())
# Define a regression fine-tune task by PaddleHub's API
reg_task = hub.RegressionTask(
feature=pooled_output,
config=config,
)
# STS-B has provided the predict data, and the dataset has process it. If you want to process customized data,
# see the predict.py in text_classification demo
# Use the appropriate tokenizer to preprocess the data
# For ernie_tiny, it will do word segmentation to get subword. More details: https://www.jiqizhixin.com/articles/2019-11-06-9
if module.name == "ernie_tiny":
tokenizer = hub.ErnieTinyTokenizer(
vocab_file=module.get_vocab_path(),
spm_path=module.get_spm_path(),
word_dict_path=module.get_word_dict_path())
else:
tokenizer = hub.BertTokenizer(vocab_file=module.get_vocab_path())
dataset = hub.dataset.GLUE("STS-B",
tokenizer=tokenizer,