# 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 feed list for data feeder
# Must feed all the tensor of module need
feed_list = [
inputs["input_ids"].name,
inputs["position_ids"].name,
inputs["segment_ids"].name,
inputs["input_mask"].name,
]
# Select finetune strategy, setup config and finetune
strategy = hub.ULMFiTStrategy(learning_rate=args.learning_rate,
params_layer=module.get_params_layer())
# Setup runing config for PaddleHub Finetune 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,
eval_interval=100)
# Define a classfication finetune task by PaddleHub's API
cls_task = hub.TextClassifierTask(data_reader=reader,
feature=pooled_output,
feed_list=feed_list,
num_classes=dataset.num_labels,
# Use the appropriate tokenizer to preprocess the data set
# For ernie_tiny, it use BertTokenizer too.
tokenizer = hub.BertTokenizer(vocab_file=module.get_vocab_path())
dataset = hub.dataset.Couplet(
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"]
sequence_output = outputs["sequence_output"]
# Select fine-tune strategy, setup config and fine-tune
strategy = hub.ULMFiTStrategy(
learning_rate=args.learning_rate,
optimizer_name="adam",
cut_fraction=args.cut_fraction,
dis_params_layer=module.get_params_layer(),
frz_params_layer=module.get_params_layer())
# 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 classfication fine-tune task by PaddleHub's API
gen_task = hub.TextGenerationTask(
dataset=dataset,
