def evaluate(args):
paddle.set_device(args.device)
# create dataset.
test_ds = load_dataset(datafiles=(os.path.join(args.data_dir, 'test.tsv')))
word_vocab = load_vocab(os.path.join(args.data_dir, 'word.dic'))
label_vocab = load_vocab(os.path.join(args.data_dir, 'tag.dic'))
# q2b.dic is used to replace DBC case to SBC case
normlize_vocab = load_vocab(os.path.join(args.data_dir, 'q2b.dic'))
trans_func = partial(
convert_example,
max_seq_len=args.max_seq_len,
word_vocab=word_vocab,
label_vocab=label_vocab,
normlize_vocab=normlize_vocab)
test_ds.map(trans_func)
batchify_fn = lambda samples, fn=Tuple(
Pad(axis=0, pad_val=0, dtype='int64'), # word_ids
Stack(dtype='int64'), # length
Pad(axis=0, pad_val=0, dtype='int64'), # label_ids
): fn(samples)
# Create sampler for dataloader
test_sampler = paddle.io.BatchSampler(
dataset=test_ds,
batch_size=args.batch_size,
shuffle=False,
drop_last=False)
test_loader = paddle.io.DataLoader(
dataset=test_ds,
batch_sampler=test_sampler,
return_list=True,
collate_fn=batchify_fn)
# Define the model network and metric evaluator
model = BiGruCrf(args.emb_dim, args.hidden_size,
len(word_vocab), len(label_vocab))
chunk_evaluator = ChunkEvaluator(label_list=label_vocab.keys(), suffix=True)
# Load the model and start predicting
model_dict = paddle.load(args.init_checkpoint)
model.load_dict(model_dict)
model.eval()
chunk_evaluator.reset()
for batch in test_loader:
token_ids, length, labels = batch
preds = model(token_ids, length)
num_infer_chunks, num_label_chunks, num_correct_chunks = chunk_evaluator.compute(
length, preds, labels)
chunk_evaluator.update(num_infer_chunks.numpy(),
num_label_chunks.numpy(),
num_correct_chunks.numpy())
precision, recall, f1_score = chunk_evaluator.accumulate()
print("eval precision: %f, recall: %f, f1: %f" %
(precision, recall, f1_score))
def main():
word_vocab = load_vocab(os.path.join(args.data_dir, 'word.dic'))
label_vocab = load_vocab(os.path.join(args.data_dir, 'tag.dic'))
model = BiGruCrf(args.emb_dim, args.hidden_size,
len(word_vocab), len(label_vocab))
state_dict = paddle.load(args.params_path)
model.set_dict(state_dict)
model.eval()
model = paddle.jit.to_static(
model,
input_spec=[
InputSpec(
shape=[None, None], dtype="int64", name='token_ids'), InputSpec(
shape=[None], dtype="int64", name='length')
])
# Save in static graph model.
paddle.jit.save(model, args.output_path)
def infer(args):
paddle.set_device(args.device)
# create dataset.
infer_ds = load_dataset(datafiles=(os.path.join(args.data_dir,
'infer.tsv')))
word_vocab = load_vocab(os.path.join(args.data_dir, 'word.dic'))
label_vocab = load_vocab(os.path.join(args.data_dir, 'tag.dic'))
# q2b.dic is used to replace DBC case to SBC case
normlize_vocab = load_vocab(os.path.join(args.data_dir, 'q2b.dic'))
trans_func = partial(
convert_example,
max_seq_len=args.max_seq_len,
word_vocab=word_vocab,
label_vocab=label_vocab,
normlize_vocab=normlize_vocab)
infer_ds.map(trans_func)
batchify_fn = lambda samples, fn=Tuple(
Pad(axis=0, pad_val=0, dtype='int64'), # word_ids
Stack(dtype='int64'), # length
): fn(samples)
# Create sampler for dataloader
infer_sampler = paddle.io.BatchSampler(
dataset=infer_ds,
batch_size=args.batch_size,
shuffle=False,
drop_last=False)
infer_loader = paddle.io.DataLoader(
dataset=infer_ds,
batch_sampler=infer_sampler,
return_list=True,
collate_fn=batchify_fn)
# Define the model network
model = BiGruCrf(args.emb_dim, args.hidden_size,
len(word_vocab), len(label_vocab))
# Load the model and start predicting
model_dict = paddle.load(args.init_checkpoint)
model.load_dict(model_dict)
model.eval()
results = []
for batch in infer_loader:
token_ids, length = batch
preds = model(token_ids, length)
result = parse_result(token_ids.numpy(),
preds.numpy(),
length.numpy(), word_vocab, label_vocab)
results += result
sent_tags = []
for sent, tags in results:
sent_tag = ['(%s, %s)' % (ch, tag) for ch, tag in zip(sent, tags)]
sent_tags.append(''.join(sent_tag))
file_path = "results.txt"
with open(file_path, "w", encoding="utf8") as fout:
fout.write("\n".join(sent_tags))
# Print some examples
print(
"The results have been saved in the file: %s, some examples are shown below: "
% file_path)
print("\n".join(sent_tags[:10]))