def load(cls,
model_path: str,
parameter_path: str,
batch_size: int = 32,
use_gpu: bool = False):
"""
Load a NPAnnotator annotator
Args:
model_path (str): path to trained model
parameter_path (str): path to model parameters
batch_size (int, optional): inference batch_size
use_gpu (bool, optional): use gpu for inference (cudnn cells)
Returns:
NPAnnotator class with loaded model
"""
_model_path = path.join(path.dirname(path.realpath(__file__)),
model_path)
validate_existing_filepath(_model_path)
_parameter_path = path.join(path.dirname(path.realpath(__file__)),
parameter_path)
validate_existing_filepath(_parameter_path)
model = SequenceChunker(use_gpu=use_gpu)
model.load(_model_path)
with open(_parameter_path, 'rb') as fp:
model_params = pickle.load(fp)
word_vocab = model_params['word_vocab']
chunk_vocab = model_params['chunk_vocab']
model.chunk_inference_mode()
return cls(model, word_vocab, chunk_vocab, batch_size)
# initialize word embedding if external model selected
if args.embedding_model is not None:
embedding_model, _ = load_word_embeddings(args.embedding_model)
embedding_mat = get_embedding_matrix(embedding_model,
dataset.word_vocab)
model.load_embedding_weights(embedding_mat)
# train the model
chunk_f1_cb = ConllCallback(words_test,
chunk_test,
dataset.chunk_vocab.vocab,
batch_size=64)
model.fit(words_train, [pos_train, chunk_train],
epochs=args.e,
batch_size=args.b,
callbacks=[chunk_f1_cb])
# save model
_save_model()
# print evaluation metric
model.chunk_inference_mode()
chunk_pred = model.predict(words_test, 64)
_, _, chunk_test = dataset.test_set
res = get_conll_scores(chunk_pred, chunk_test,
dataset.chunk_vocab.reverse_vocab())
if args.print_np is True:
print('NP F1: {}'.format(res[1]['NP'][-1]))
else:
print('Chunk F1: {}'.format(res[0][-1]))