def _make_eval_prediction_hooks_fn(self):
external_scorers = self._config["eval"].get("external_evaluators")
if not self._config["eval"].get("save_eval_predictions",
False) and external_scorers is None:
return None
if self._model.unsupervised:
raise RuntimeError(
"This model does not support saving evaluation predictions")
save_path = os.path.join(self._config["model_dir"], "eval")
if not tf.gfile.Exists(save_path):
tf.gfile.MakeDirs(save_path)
if external_scorers is not None:
external_evaluator = evaluator.ExternalEvaluator(
labels_file=self._config["data"]["eval_labels_file"],
output_dir=os.path.join(self._config["model_dir"],
"external_eval"),
scorers=evaluator.make_scorers(external_scorers))
else:
external_evaluator = None
return lambda predictions: [
hooks.SaveEvaluationPredictionHook(
self._model,
os.path.join(save_path, "predictions.txt"),
post_evaluation_fn=external_evaluator,
predictions=predictions)
]
def _build_eval_spec(self):
if "eval" not in self._config:
self._config["eval"] = {}
eval_hooks = []
if (self._config["eval"].get("save_eval_predictions", False)
or self._config["eval"].get("external_evaluators") is not None):
save_path = os.path.join(self._estimator.model_dir, "eval")
if not os.path.isdir(save_path):
os.makedirs(save_path)
eval_hooks.append(hooks.SaveEvaluationPredictionHook(
self._model,
os.path.join(save_path, "predictions.txt"),
post_evaluation_fn=external_evaluation_fn(
self._config["eval"].get("external_evaluators"),
self._config["data"]["eval_labels_file"],
output_dir=self._estimator.model_dir)))
eval_spec = tf.estimator.EvalSpec(
input_fn=self._model.input_fn(
tf.estimator.ModeKeys.EVAL,
self._config["eval"].get("batch_size", 32),
self._config["data"],
self._config["data"]["eval_features_file"],
num_threads=self._config["eval"].get("num_threads"),
prefetch_buffer_size=self._config["eval"].get("prefetch_buffer_size"),
labels_file=self._config["data"]["eval_labels_file"]),
steps=None,
hooks=eval_hooks,
exporters=_make_exporters(
self._config["eval"].get("exporters", "last"),
self._model.serving_input_fn(self._config["data"])),
throttle_secs=self._config["eval"].get("eval_delay", 18000))
return eval_spec
def _make_eval_prediction_hooks_fn(self):
if (not self._config["eval"].get("save_eval_predictions", False)
and self._config["eval"].get("external_evaluators") is None):
return None
save_path = os.path.join(self._config["model_dir"], "eval")
if not tf.gfile.Exists(save_path):
tf.gfile.MakeDirs(save_path)
return lambda predictions: [
hooks.SaveEvaluationPredictionHook(
self._model,
os.path.join(save_path, "predictions.txt"),
post_evaluation_fn=external_evaluation_fn(
self._config["eval"].get("external_evaluators"),
self._config["data"]["eval_labels_file"],
output_dir=save_path),
predictions=predictions)]
def train(estimator, model, config):
"""Runs training.
Args:
estimator: A `tf.estimator.Estimator`.
model: A `opennmt.models.Model`.
config: The configuration.
"""
batch_size = config["train"]["batch_size"]
prefetch_buffer_size = config["train"].get("prefetch_buffer_size",
batch_size * 1000)
num_parallel_process_calls = config["train"].get(
"num_parallel_process_calls", multiprocessing.cpu_count())
train_hooks = [
hooks.LogParametersCountHook(),
hooks.CountersHook(every_n_steps=estimator.config.save_summary_steps,
output_dir=estimator.model_dir)
]
eval_hooks = []
if config["train"].get("save_eval_predictions", False):
save_path = os.path.join(estimator.model_dir, "eval")
if not os.path.isdir(save_path):
os.makedirs(save_path)
eval_hooks.append(
hooks.SaveEvaluationPredictionHook(
model,
os.path.join(save_path, "predictions.txt"),
post_evaluation_fn=external_evaluation_fn(
config["train"].get("external_evaluators"),
config["data"]["eval_labels_file"],
output_dir=estimator.model_dir)))
elif config["train"].get("external_evaluators") is not None:
tf.logging.warning(
"External evaluators only work when save_eval_predictions is enabled."
)
train_spec = tf.estimator.TrainSpec(input_fn=model.input_fn(
tf.estimator.ModeKeys.TRAIN,
batch_size,
prefetch_buffer_size,
num_parallel_process_calls,
config["data"],
config["data"]["train_features_file"],
labels_file=config["data"]["train_labels_file"],
num_buckets=config["train"].get("num_buckets", 5),
sample_buffer_size=config["train"].get("sample_buffer_size", 1000000),
maximum_features_length=config["train"].get("maximum_features_length"),
maximum_labels_length=config["train"].get("maximum_labels_length")),
max_steps=config["train"].get(
"train_steps"),
hooks=train_hooks)
eval_spec = tf.estimator.EvalSpec(
input_fn=model.input_fn(
tf.estimator.ModeKeys.EVAL,
batch_size,
prefetch_buffer_size,
num_parallel_process_calls,
config["data"],
config["data"]["eval_features_file"],
labels_file=config["data"]["eval_labels_file"]),
steps=None,
hooks=eval_hooks,
exporters=tf.estimator.LatestExporter(
"latest", model.serving_input_fn(config["data"])),
throttle_secs=config["train"].get("eval_delay", 18000))
tf.estimator.train_and_evaluate(estimator, train_spec, eval_spec)
def train(estimator, model, config):
"""Runs training.
Args:
estimator: A `tf.estimator.Estimator`.
model: A `opennmt.models.Model`.
config: The configuration.
"""
if "eval" not in config:
config["eval"] = {}
train_hooks = [
hooks.LogParametersCountHook(),
hooks.CountersHook(every_n_steps=estimator.config.save_summary_steps,
output_dir=estimator.model_dir)
]
eval_hooks = []
if (config["eval"].get("save_eval_predictions", False)
or config["eval"].get("external_evaluators") is not None):
save_path = os.path.join(estimator.model_dir, "eval")
if not os.path.isdir(save_path):
os.makedirs(save_path)
eval_hooks.append(
hooks.SaveEvaluationPredictionHook(
model,
os.path.join(save_path, "predictions.txt"),
post_evaluation_fn=external_evaluation_fn(
config["eval"].get("external_evaluators"),
config["data"]["eval_labels_file"],
output_dir=estimator.model_dir)))
default_sample_buffer_size = 1000000
if "sample_buffer_size" not in config["train"]:
tf.logging.warn(
"You did not set sample_buffer_size. By default, the "
"training dataset is shuffled by chunk of %d examples. "
"If your dataset is larger than this value and eval_delay "
"is shorter than the training time of one epoch, a section "
"of the dataset will be discarded. Consider setting "
"sample_buffer_size to the size of your dataset." %
default_sample_buffer_size)
train_batch_size = config["train"]["batch_size"]
train_batch_type = config["train"].get("batch_type", "examples")
train_prefetch_buffer_size = config["train"].get(
"prefetch_buffer_size",
train_batch_size * (1000 if train_batch_type == "examples" else 50))
train_num_parallel_process_calls = config["train"].get(
"num_parallel_process_calls", multiprocessing.cpu_count())
train_spec = tf.estimator.TrainSpec(input_fn=model.input_fn(
tf.estimator.ModeKeys.TRAIN,
train_batch_size,
train_prefetch_buffer_size,
train_num_parallel_process_calls,
config["data"],
config["data"]["train_features_file"],
labels_file=config["data"]["train_labels_file"],
batch_type=train_batch_type,
bucket_width=config["train"].get("bucket_width", 5),
sample_buffer_size=config["train"].get("sample_buffer_size",
default_sample_buffer_size),
maximum_features_length=config["train"].get("maximum_features_length"),
maximum_labels_length=config["train"].get("maximum_labels_length")),
max_steps=config["train"].get(
"train_steps"),
hooks=train_hooks)
eval_batch_size = config["eval"].get(
"batch_size",
train_batch_size if train_batch_type == "examples" else 30)
eval_prefetch_buffer_size = config["eval"].get("prefetch_buffer_size",
eval_batch_size * 10)
eval_num_parallel_process_calls = config["eval"].get(
"num_parallel_process_calls", train_num_parallel_process_calls)
eval_spec = tf.estimator.EvalSpec(
input_fn=model.input_fn(
tf.estimator.ModeKeys.EVAL,
eval_batch_size,
eval_prefetch_buffer_size,
eval_num_parallel_process_calls,
config["data"],
config["data"]["eval_features_file"],
labels_file=config["data"]["eval_labels_file"]),
steps=None,
hooks=eval_hooks,
exporters=tf.estimator.LatestExporter(
"latest", model.serving_input_fn(config["data"])),
throttle_secs=config["eval"].get("eval_delay", 18000))
tf.estimator.train_and_evaluate(estimator, train_spec, eval_spec)
