def predict_line(text):
dataset = tf.keras.preprocessing.sequence.pad_sequences([[word_to_id.get(char, 0) for char in text]],
padding='post')
logits, text_lens = model.predict(dataset)
paths = []
for logit, text_len in zip(logits, text_lens):
viterbi_path, _ = tf_ad.text.viterbi_decode(logit[:text_len], model.transition_params)
paths.append(viterbi_path)
entities_result = data_utils.format_result(list(text), [id_to_tag[id] for id in paths[0]])
return entities_result
config.n_vocab = len(word_to_id)
time_dif = data_utils.get_time_dif(start_time)
print("Time usage:", time_dif)
# train
model = x.MyModel(config)
optimizer = tf.keras.optimizers.Adam(config.learning_rate)
ckpt = tf.train.Checkpoint(optimizer=optimizer, model=model)
ckpt.restore(tf.train.latest_checkpoint(config.save_path))
while True:
text = input("input:")
dataset = tf.keras.preprocessing.sequence.pad_sequences(
[[word_to_id.get(char, 0) for char in text]], padding='post')
print(dataset)
logits, text_lens = model.predict(dataset)
paths = []
for logit, text_len in zip(logits, text_lens):
viterbi_path, _ = tf_ad.text.viterbi_decode(
logit[:text_len], model.transition_params)
paths.append(viterbi_path)
print(paths[0])
print([id_to_tag[id] for id in paths[0]])
entities_result = data_utils.format_result(
list(text), [id_to_tag[id] for id in paths[0]])
print(json.dumps(entities_result, indent=4, ensure_ascii=False))