def load_saved_model():
if model_type == 'seq2seq':
model = Seq2SeqIntentModel()
else:
model = MultiTaskIntentModel()
model.load(args.model_path)
return model
def load_model(self):
if self.model_type == 'seq2seq':
model = Seq2SeqIntentModel()
else:
model = MultiTaskIntentModel()
model.load(self.pretrained_model)
self.model = model
def load_model(self):
with open(IntentExtractionApi.pretrained_model_info, "rb") as fp:
model_info = pickle.load(fp)
self.model_type = model_info["type"]
self.word_vocab = model_info["word_vocab"]
self.tags_vocab = {v: k for k, v in model_info["tags_vocab"].items()}
if self.model_type == "mtl":
self.char_vocab = model_info["char_vocab"]
self.intent_vocab = {
v: k
for k, v in model_info["intent_vocab"].items()
}
model = MultiTaskIntentModel()
else:
model = Seq2SeqIntentModel()
model.load(self.pretrained_model)
self.model = model
def load_model(self):
with open(IntentExtractionApi.pretrained_model_info, 'rb') as fp:
model_info = pickle.load(fp)
self.model_type = model_info['type']
self.word_vocab = model_info['word_vocab']
self.tags_vocab = {v: k for k, v in model_info['tags_vocab'].items()}
if self.model_type == 'mtl':
self.char_vocab = model_info['char_vocab']
self.intent_vocab = {
v: k
for k, v in model_info['intent_vocab'].items()
}
model = MultiTaskIntentModel()
else:
model = Seq2SeqIntentModel()
model.load(self.pretrained_model)
self.model = model
parser.add_argument('--model_info_path',
type=str,
default='model_info.dat',
help='Path for saving model topology')
args = parser.parse_args()
validate_input_args()
dataset = SNIPS(path=args.dataset_path,
sentence_length=args.sentence_length)
train_x, _, train_i, train_y = dataset.train_set
test_x, _, test_i, test_y = dataset.test_set
test_y = to_categorical(test_y, dataset.label_vocab_size)
train_y = to_categorical(train_y, dataset.label_vocab_size)
model = Seq2SeqIntentModel()
model.build(dataset.word_vocab_size, dataset.label_vocab_size,
args.token_emb_size, args.encoder_depth, args.decoder_depth,
args.lstm_hidden_size, args.encoder_dropout,
args.decoder_dropout)
conll_cb = ConllCallback(test_x,
test_y,
dataset.tags_vocab.vocab,
batch_size=args.b)
# train model
model.fit(x=train_x,
y=train_y,
batch_size=args.b,
epochs=args.e,