def testTextInputterTest(self):
vocab_src = Vocab(vocab_src_file)
vocab_trg = Vocab(vocab_trg_file)
dataset = Dataset(vocab_src, vocab_trg,
train_src_file, train_trg_file,
[eval_src_file], eval_trg_file)
test_iter = TestTextIterator(
train_src_file,
vocab_src,
batch_size=13)
inputter = TextLineInputter(
dataset,
"eval_features_file",
batch_size=13)
input_fields = dataset.input_fields
test_data = inputter.make_feeding_data()
for a, b in zip(test_iter, test_data[0]):
x_str = a[0]
x = a[1][0]
x_len = a[1][1]
x_str_new = b[0]
x_new = b[2][input_fields[Constants.FEATURE_IDS_NAME]]
x_len_new = b[2][input_fields[Constants.FEATURE_LENGTH_NAME]]
assert x.all() == x_new.all()
assert x_len.all() == x_len_new.all()
assert numpy.all([str1 == str2 for str1, str2 in zip(x_str, x_str_new)])
print("Test Passed...")
def _prepare(self):
""" Prepares for evaluation.
Builds the model with reuse=True, mode=EVAL and preprocesses
data file(s).
"""
text_inputter = TextLineInputter(dataset=self._dataset,
data_field_name="eval_features_file",
batch_size=self._batch_size)
self._eval_feeding_data = text_inputter.make_feeding_data()
self._model_configs = update_infer_params( # update inference parameters
self._model_configs,
beam_size=self._beam_size,
maximum_labels_length=self._maximum_labels_length,
length_penalty=self._length_penalty)
estimator_spec = model_fn(model_configs=self._model_configs,
mode=ModeKeys.INFER,
dataset=self._dataset,
name=self._model_name,
reuse=True,
verbose=False)
self._predict_ops = estimator_spec.predictions
tmp_trans_dir = os.path.join(self._model_configs["model_dir"],
GlobalNames.TMP_TRANS_DIRNAME)
if not gfile.Exists(tmp_trans_dir):
gfile.MakeDirs(tmp_trans_dir)
self._tmp_trans_file_prefix = os.path.join(
tmp_trans_dir, GlobalNames.TMP_TRANS_FILENAME_PREFIX)
self._read_ckpt_bleulog()
self._eval_labels_file = self._dataset.eval_labels_file
self._check_bleu_script()
self._estop_patience = 0
self._best_bleu_score = 0.
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"],
maximum_line_length=None)
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,
alpha=self._model_configs["infer"]["length_penalty"],
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. """
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 _prepare(self):
""" Prepares for evaluation.
Builds the model with reuse=True, mode=EVAL and preprocesses
data file(s).
"""
features_file = self._dataset["features_file"]
labels_file = self._dataset["labels_file"]
vocab_source = self._dataset["vocab_source"]
vocab_target = self._dataset["vocab_target"]
self._model_configs = update_infer_params( # update inference parameters
self._model_configs,
beam_size=self._beam_size,
maximum_labels_length=self._maximum_labels_length,
length_penalty=self._length_penalty)
estimator_spec = model_fn(model_configs=self._model_configs,
mode=ModeKeys.INFER,
vocab_source=vocab_source,
vocab_target=vocab_target,
name=self._model_name, reuse=True,
verbose=False)
self._predict_ops = estimator_spec.predictions
text_inputter = TextLineInputter(
line_readers=LineReader(
data=features_file,
preprocessing_fn=lambda x: vocab_source.convert_to_idlist(x)),
padding_id=vocab_source.pad_id,
batch_size=self._batch_size)
self._infer_data = text_inputter.make_feeding_data(
input_fields=estimator_spec.input_fields)
tmp_trans_dir = os.path.join(self._model_configs["model_dir"], Constants.TMP_TRANS_DIRNAME)
if not gfile.Exists(tmp_trans_dir):
gfile.MakeDirs(tmp_trans_dir)
self._tmp_trans_file_prefix = os.path.join(tmp_trans_dir, Constants.TMP_TRANS_FILENAME_PREFIX)
self._read_ckpt_bleulog()
# load references
self._references = []
for rfile in access_multiple_files(labels_file):
with open_file(rfile) as fp:
if self._char_level:
self._references.append(to_chinese_char(fp.readlines()))
else:
self._references.append(fp.readlines())
self._references = list(map(list, zip(*self._references)))
with open_file(features_file) as fp:
self._sources = fp.readlines()
self._bad_count = 0
self._best_bleu_score = 0.
def _prepare(self):
""" Prepares for evaluation.
Builds the model with reuse=True, mode=EVAL and preprocesses
data file(s).
"""
text_inputter = TextLineInputter(dataset=self._dataset,
data_field_name="eval_features_file",
batch_size=self._batch_size)
self._infer_data = text_inputter.make_feeding_data()
self._model_configs = update_infer_params( # update inference parameters
self._model_configs,
beam_size=self._beam_size,
maximum_labels_length=self._maximum_labels_length,
length_penalty=self._length_penalty)
estimator_spec = model_fn(model_configs=self._model_configs,
mode=ModeKeys.INFER,
dataset=self._dataset,
name=self._model_name,
reuse=True,
verbose=False)
self._predict_ops = estimator_spec.predictions
tmp_trans_dir = os.path.join(self._model_configs["model_dir"],
Constants.TMP_TRANS_DIRNAME)
if not gfile.Exists(tmp_trans_dir):
gfile.MakeDirs(tmp_trans_dir)
self._tmp_trans_file_prefix = os.path.join(
tmp_trans_dir, Constants.TMP_TRANS_FILENAME_PREFIX)
self._read_ckpt_bleulog()
# load references
self._references = []
for rfile in self._dataset.eval_labels_file:
with open_file(rfile) as fp:
self._references.append(fp.readlines())
self._references = list(map(list, zip(*self._references)))
with open_file(self._dataset.eval_features_file) as fp:
self._sources = fp.readlines()
self._bad_count = 0
self._best_bleu_score = 0.
def run(self):
"""Infers data files. """
# build datasets
self._vocab_source = Vocab(
filename=self._model_configs["infer"]["source_words_vocabulary"],
bpe_codes=self._model_configs["infer"]["source_bpecodes"],
reverse_seq=False)
self._vocab_target = Vocab(
filename=self._model_configs["infer"]["target_words_vocabulary"],
bpe_codes=self._model_configs["infer"]["target_bpecodes"],
reverse_seq=self._model_configs["train"]["reverse_target"])
# build dataset
dataset = Dataset(
self._vocab_source,
self._vocab_target,
eval_features_file=[p["features_file"] for p
in self._model_configs["infer_data"]])
self._model_configs = update_infer_params(
self._model_configs,
beam_size=self._model_configs["infer"]["beam_size"],
maximum_labels_length=self._model_configs["infer"]["maximum_labels_length"],
length_penalty=self._model_configs["infer"]["length_penalty"])
# build model
estimator_spec = model_fn(model_configs=self._model_configs,
mode=ModeKeys.INFER,
dataset=dataset,
name=self._model_configs["problem_name"])
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"])
# reload
checkpoint_path = tf.train.latest_checkpoint(self._model_configs["model_dir"])
if checkpoint_path:
tf.logging.info("reloading models...")
saver = tf.train.Saver()
saver.restore(sess, checkpoint_path)
else:
raise OSError("File NOT Found. Fail to find checkpoint file from: {}"
.format(self._model_configs["model_dir"]))
tf.logging.info("Start inference.")
overall_start_time = time.time()
for infer_data, param in zip(text_inputter.make_feeding_data(
input_fields=estimator_spec.input_fields),
self._model_configs["infer_data"]):
tf.logging.info("Infer Source File: {}.".format(param["features_file"]))
start_time = time.time()
infer(sess=sess,
prediction_op=predict_op,
infer_data=infer_data,
output=param["output_file"],
vocab_source=self._vocab_source,
vocab_target=self._vocab_target,
delimiter=self._model_configs["infer"]["delimiter"],
output_attention=param["output_attention"],
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))