def train(train_i, args):
dataset = MyDataset()
module = hub.Module(name=args.model)
reader = hub.reader.MultiLabelClassifyReader(
dataset=dataset,
vocab_path=module.get_vocab_path(),
max_seq_len=args.max_seq_len)
strategy = hub.AdamWeightDecayStrategy(
weight_decay=args.weight_decay,
warmup_proportion=args.warmup_proportion,
lr_scheduler=args.lr_scheduler,
learning_rate=args.learning_rate)
config = hub.RunConfig(use_cuda=args.use_gpu,
num_epoch=args.num_epoch,
checkpoint_dir=args.checkpoint_dir + str(train_i),
batch_size=args.batch_size,
eval_interval=eval_interval,
log_interval=log_interval,
strategy=strategy)
inputs, outputs, program = module.context(trainable=True,
max_seq_len=args.max_seq_len)
# Use "pooled_output" for classification tasks on an entire sentence.
pooled_output = outputs["pooled_output"]
# feed_list的Tensor顺序不可以调整
feed_list = [
inputs["input_ids"].name,
inputs["position_ids"].name,
inputs["segment_ids"].name,
inputs["input_mask"].name,
]
cls_task = hub.MultiLabelClassifierTask(data_reader=reader,
feature=pooled_output,
feed_list=feed_list,
num_classes=dataset.num_labels,
config=config)
cls_task.main_program.random_seed = args.seed
change_task(cls_task, train_i)
return cls_task, reader
max_seq_len=args.max_seq_len,
use_task_id=args.use_taskid)
# Construct transfer learning network
# Use "pooled_output" for classification tasks on an entire sentence.
pooled_output = outputs["pooled_output"]
# 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_cuda=args.use_gpu,
num_epoch=args.num_epoch,
batch_size=args.batch_size,
checkpoint_dir=args.checkpoint_dir,
strategy=strategy)
# Define a classfication finetune task by PaddleHub's API
multi_label_cls_task = hub.MultiLabelClassifierTask(
data_reader=reader,
feature=pooled_output,
feed_list=feed_list,
num_classes=dataset.num_labels,
config=config)
# Finetune and evaluate by PaddleHub's API
# will finish training, evaluation, testing, save model automatically
multi_label_cls_task.finetune_and_eval()
dataset = hub.dataset.Toxic(tokenizer=tokenizer,
max_seq_len=args.max_seq_len)
# Construct transfer learning network
# Use "pooled_output" for classification tasks on an entire sentence.
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_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
multi_label_cls_task = hub.MultiLabelClassifierTask(
dataset=dataset,
feature=pooled_output,
num_classes=dataset.num_labels,
config=config)
# Fine-tune and evaluate by PaddleHub's API
# will finish training, evaluation, testing, save model automatically
multi_label_cls_task.finetune_and_eval()
