def main(args):
place = set_device(args.device)
fluid.enable_dygraph(place) if args.dynamic else None
inputs = [
Input(
[None, None], 'int64', name='words'), Input(
[None], 'int64', name='length')
]
dataset = LacDataset(args)
predict_dataset = LacDataLoader(args, place, phase="predict")
vocab_size = dataset.vocab_size
num_labels = dataset.num_labels
model = SeqTagging(args, vocab_size, num_labels, mode="predict")
model.mode = "test"
model.prepare(inputs=inputs)
model.load(args.init_from_checkpoint, skip_mismatch=True)
f = open(args.output_file, "wb")
for data in predict_dataset.dataloader:
if len(data) == 1:
input_data = data[0]
else:
input_data = data
results, length = model.test_batch(inputs=flatten(input_data))
for i in range(len(results)):
word_len = length[i]
word_ids = results[i][:word_len]
tags = [dataset.id2label_dict[str(id)] for id in word_ids]
f.write("\002".join(tags) + "\n")
def main(args):
place = set_device(args.device)
fluid.enable_dygraph(place) if args.dynamic else None
inputs = [
Input([None, None], 'int64', name='words'),
Input([None], 'int64', name='length'),
Input([None, None], 'int64', name='target')
]
labels = [Input([None, None], 'int64', name='labels')]
dataset = LacDataset(args)
eval_dataset = LacDataLoader(args, place, phase="test")
vocab_size = dataset.vocab_size
num_labels = dataset.num_labels
model = SeqTagging(args, vocab_size, num_labels, mode="test")
model.mode = "test"
model.prepare(metrics=ChunkEval(num_labels),
inputs=inputs,
labels=labels,
device=place)
model.load(args.init_from_checkpoint, skip_mismatch=True)
eval_result = model.evaluate(eval_dataset.dataloader,
batch_size=args.batch_size)
print("precison: %.5f" % (eval_result["precision"][0]))
print("recall: %.5f" % (eval_result["recall"][0]))
print("F1: %.5f" % (eval_result["F1"][0]))
def main(args):
place = set_device(args.device)
fluid.enable_dygraph(place) if args.dynamic else None
inputs = [
Input(
[None, None], 'int64', name='words'), Input(
[None], 'int64', name='length'), Input(
[None, None], 'int64', name='target')
]
labels = [Input([None, None], 'int64', name='labels')]
feed_list = None if args.dynamic else [
x.forward() for x in inputs + labels
]
dataset = LacDataset(args)
train_dataset = LacDataLoader(args, place, phase="train")
vocab_size = dataset.vocab_size
num_labels = dataset.num_labels
model = SeqTagging(args, vocab_size, num_labels, mode="train")
optim = AdamOptimizer(
learning_rate=args.base_learning_rate,
parameter_list=model.parameters())
model.prepare(
optim,
LacLoss(),
ChunkEval(num_labels),
inputs=inputs,
labels=labels,
device=args.device)
if args.init_from_checkpoint:
model.load(args.init_from_checkpoint)
if args.init_from_pretrain_model:
model.load(args.init_from_pretrain_model, reset_optimizer=True)
model.fit(train_dataset.dataloader,
epochs=args.epoch,
batch_size=args.batch_size,
eval_freq=args.eval_freq,
save_freq=args.save_freq,
save_dir=args.save_dir)