def run(self):
""" Runs ensemble model. """
vocab_source = Vocab(
filename=self._model_configs["infer"]["source_words_vocabulary"],
bpe_codes=self._model_configs["infer"]["source_bpecodes"])
vocab_target = Vocab(
filename=self._model_configs["infer"]["target_words_vocabulary"],
bpe_codes=self._model_configs["infer"]["target_bpecodes"])
estimator_spec = model_fn_ensemble(
self._model_dirs,
vocab_source,
vocab_target,
weight_scheme=self._weight_scheme,
inference_options=self._model_configs["infer"])
predict_op = estimator_spec.predictions
sess = self._build_default_session()
text_inputter = TextLineInputter(line_readers=[
LineReader(
data=p["features_file"],
preprocessing_fn=lambda x: vocab_source.convert_to_idlist(x))
for p in self._model_configs["infer_data"]
],
padding_id=vocab_source.pad_id,
batch_size=self.
_model_configs["infer"]["batch_size"])
sess.run(tf.global_variables_initializer())
tf.logging.info("Start inference.")
overall_start_time = time.time()
for feeding_data, param in zip(
text_inputter.make_feeding_data(estimator_spec.input_fields),
self._model_configs["infer_data"]):
tf.logging.info("Infer Source Features File: {}.".format(
param["features_file"]))
start_time = time.time()
infer(sess=sess,
prediction_op=predict_op,
infer_data=feeding_data,
output=param["output_file"],
vocab_source=vocab_source,
vocab_target=vocab_target,
delimiter=self._model_configs["infer"]["delimiter"],
output_attention=False,
to_char_level=self._model_configs["infer"]["char_level"],
verbose=True)
tf.logging.info("FINISHED {}. Elapsed Time: {}.".format(
param["features_file"], str(time.time() - start_time)))
if param["labels_file"] is not None:
bleu_score = multi_bleu_score_from_file(
hypothesis_file=param["output_file"],
references_files=param["labels_file"],
char_level=self._model_configs["infer"]["char_level"])
tf.logging.info("BLEU score (%s): %.2f" %
(param["features_file"], bleu_score))
tf.logging.info("Total Elapsed Time: %s" %
str(time.time() - overall_start_time))
def run(self):
""" Runs ensemble model. """
self._vocab_source = Vocab(
filename=self._model_configs["infer"]["source_words_vocabulary"],
bpe_codes_file=self._model_configs["infer"]["source_bpecodes"])
self._vocab_target = Vocab(
filename=self._model_configs["infer"]["target_words_vocabulary"],
bpe_codes_file=self._model_configs["infer"]["target_bpecodes"])
# build dataset
dataset = Dataset(self._vocab_source,
self._vocab_target,
eval_features_file=[
p["features_file"]
for p in self._model_configs["infer_data"]
])
estimator_spec = model_fn_ensemble(
self._model_dirs,
dataset,
weight_scheme=self._weight_scheme,
inference_options=self._model_configs["infer"])
predict_op = estimator_spec.predictions
sess = self._build_default_session()
text_inputter = TextLineInputter(
dataset=dataset,
data_field_name="eval_features_file",
batch_size=self._model_configs["infer"]["batch_size"])
sess.run(tf.global_variables_initializer())
tf.logging.info("Start inference.")
overall_start_time = time.time()
for feeding_data, param in zip(text_inputter.make_feeding_data(),
self._model_configs["infer_data"]):
tf.logging.info("Infer Source Features File: {}.".format(
param["features_file"]))
start_time = time.time()
infer(sess=sess,
prediction_op=predict_op,
feeding_data=feeding_data,
output=param["output_file"],
vocab_target=self._vocab_target,
delimiter=self._model_configs["infer"]["delimiter"],
output_attention=False,
tokenize_output=self._model_configs["infer"]["char_level"],
tokenize_script=self._model_configs["infer"]
["tokenize_script"],
verbose=True)
tf.logging.info("FINISHED {}. Elapsed Time: {}.".format(
param["features_file"], str(time.time() - start_time)))
if param["labels_file"] is not None:
bleu_score = multi_bleu_score(
self._model_configs["infer"]["multibleu_script"],
param["labels_file"], param["output_file"])
tf.logging.info("BLEU score ({}): {}".format(
param["features_file"], bleu_score))
tf.logging.info("Total Elapsed Time: %s" %
str(time.time() - overall_start_time))
def run(self):
""" Runs ensemble model. """
self._vocab_source = Vocab(
filename=self._model_configs["infer"]["source_words_vocabulary"],
bpe_codes=self._model_configs["infer"]["source_bpecodes"])
self._vocab_target = Vocab(
filename=self._model_configs["infer"]["target_words_vocabulary"],
bpe_codes=self._model_configs["infer"]["target_bpecodes"])
# build dataset
dataset = Dataset(
self._vocab_source,
self._vocab_target,
eval_features_file=[p["features_file"] for p
in self._model_configs["infer_data"]])
estimator_spec = model_fn_ensemble(
self._model_dirs, dataset, weight_scheme=self._weight_scheme,
inference_options=self._model_configs["infer"])
predict_op = estimator_spec.predictions
sess = self._build_default_session()
text_inputter = TextLineInputter(
dataset=dataset,
data_field_name="eval_features_file",
batch_size=self._model_configs["infer"]["batch_size"])
sess.run(tf.global_variables_initializer())
tf.logging.info("Start inference.")
overall_start_time = time.time()
for feeding_data, param in zip(text_inputter.make_feeding_data(estimator_spec.input_fields),
self._model_configs["infer_data"]):
tf.logging.info("Infer Source Features File: {}.".format(param["features_file"]))
start_time = time.time()
infer(sess=sess,
prediction_op=predict_op,
infer_data=feeding_data,
output=param["output_file"],
vocab_source=self._vocab_source,
vocab_target=self._vocab_target,
delimiter=self._model_configs["infer"]["delimiter"],
output_attention=False,
tokenize_output=self._model_configs["infer"]["char_level"],
verbose=True)
tf.logging.info("FINISHED {}. Elapsed Time: {}."
.format(param["features_file"], str(time.time() - start_time)))
if param["labels_file"] is not None:
bleu_score = multi_bleu_score_from_file(
hypothesis_file=param["output_file"],
references_files=param["labels_file"],
char_level=self._model_configs["infer"]["char_level"])
tf.logging.info("BLEU score (%s): %.2f"
% (param["features_file"], bleu_score))
tf.logging.info("Total Elapsed Time: %s" % str(time.time() - overall_start_time))