def run_inference(model_dir: str, epoch: Optional[int], device: str, metric: str):
chainer.config.train = False
if device >= 0:
cuda.get_device(device).use()
set_seed()
configs = json.load(open(os.path.join(model_dir, "args")))
snapshot_file, prediction_path = select_snapshot(epoch, metric, model_dir)
logger.debug(f"creat prediction into {prediction_path}")
vocab = Vocabulary.prepare(configs)
num_word_vocab = configs["num_word_vocab"]
num_char_vocab = configs["num_char_vocab"]
num_tag_vocab = configs["num_tag_vocab"]
model = BiLSTM_CRF(configs, num_word_vocab, num_char_vocab, num_tag_vocab)
model_path = os.path.join(model_dir, snapshot_file)
chainer.serializers.load_npz(model_path, model)
logger.debug(f"load {snapshot_file}")
if device >= 0:
model.to_gpu(device)
transformer = DatasetTransformer(vocab)
transform = transformer.transform
test_iterator = create_iterator(
vocab, configs, "test", transform, return_original_sentence=True
)
with open(prediction_path, "w", encoding="utf-8") as file:
for batch in test_iterator:
batch, original_sentences = list(zip(*batch))
in_arrays, t_arrays = converter(batch, device)
p_arrays = model.predict(in_arrays)
word_sentences, t_tag_sentences = list(
zip(*transformer.itransform(in_arrays[0], t_arrays))
)
_, p_tag_sentences = list(
zip(*transformer.itransform(in_arrays[0], p_arrays))
)
sentence_gen = zip(
word_sentences,
t_tag_sentences,
p_tag_sentences,
original_sentences,
) # NOQA
for ws, ts, ps, _os in sentence_gen:
for w, t, p, o in zip(ws, ts, ps, _os):
w = w.replace(" ", "<WHITESPACE>")
o = o.replace(" ", "<WHITESPACE>")
if w != o:
w = f"{w}({o})"
print(f"{w} {t} {p}", file=file)
print(file=file)
def run_inference(
model_dir: str,
epoch: Optional[int],
device: str,
metric: str,
tokenizer: str):
chainer.config.train = False
if device >= 0:
chainer.get_device(device).use()
set_seed()
config = json.load(open(os.path.join(model_dir, "args")))
snapshot_file, prediction_path = select_snapshot(epoch, metric, model_dir)
logger.debug(f"creat prediction into {prediction_path}")
vocab = Vocabulary.prepare(config)
num_word_vocab = config["num_word_vocab"]
num_char_vocab = config["num_char_vocab"]
num_tag_vocab = config["num_tag_vocab"]
model = BiLSTM_CRF(config, num_word_vocab, num_char_vocab, num_tag_vocab)
model_path = os.path.join(model_dir, snapshot_file)
logger.debug(f"load {snapshot_file}")
chainer.serializers.load_npz(model_path, model)
if device >= 0:
model.to_gpu(device)
transformer = DatasetTransformer(vocab)
word_tokenizer = WordTokenizer(tokenizer=tokenizer)
for line in sys.stdin:
input_sentence = [str(t) for t in word_tokenizer.tokenize(line)]
batch = transformer.transform(input_sentence, None)
in_arr, _ = converter([batch])
pd_arr = model.predict(in_arr)
(_, tag_sequence), = transformer.itransform(in_arr[0], pd_arr)
print(' '.join(f"{word}/{tag}" for word, tag in zip(input_sentence, tag_sequence))) # NOQA
model = BiLSTM_CRF(configs, num_word_vocab, num_char_vocab, num_tag_vocab)
model_path = model_dir / snapshot_file
logger.debug(f'load {snapshot_file}')
chainer.serializers.load_npz(model_path.as_posix(), model)
if args.device >= 0:
model.to_gpu(args.device)
transformer = DatasetTransformer(vocab)
transform = transformer.transform
test_iterator = create_iterator(vocab, configs, 'test', transform)
with open(prediction_path, 'w', encoding='utf-8') as file:
for batch in test_iterator:
in_arrays, t_arrays = converter(batch, args.device)
p_arrays = model.predict(in_arrays)
word_sentences, t_tag_sentences = list(
zip(*transformer.itransform(in_arrays[0], t_arrays)))
_, p_tag_sentences = list(
zip(*transformer.itransform(in_arrays[0], p_arrays)))
sentence_gen = zip(word_sentences, t_tag_sentences,
p_tag_sentences) # NOQA
for ws, ts, ps in sentence_gen:
for w, t, p in zip(ws, ts, ps):
print(f'{w} {t} {p}', file=file)
print(file=file)