def make_input(self, batch_dict, train=False):
"""When we are running with `DataFeed`s, need to transform to `feed_dict`s
:param batch_dict: The batch for a step
:param train: (`bool`) Are we training (or evaluating)?
:return: A `feed_dict`
"""
if not tf.executing_eagerly():
batch_dict_for_model = new_placeholder_dict(train)
for key in self.src_keys:
batch_dict_for_model["{}:0".format(key)] = batch_dict[key]
y = batch_dict.get('y')
if y is not None:
batch_dict_for_model[self.y] = batch_dict['y']
else:
SET_TRAIN_FLAG(train)
batch_dict_for_model = {}
for key in self.src_keys:
batch_dict_for_model[key] = batch_dict[key]
return batch_dict_for_model
def make_input(self, batch_dict, train=False):
"""Transform a `batch_dict` into a TensorFlow `feed_dict`
:param batch_dict: (``dict``) A dictionary containing all inputs to the embeddings for this model
:param train: (``bool``) Are we training. Defaults to False
:return:
"""
y = batch_dict.get('y', None)
if not tf.executing_eagerly():
batch_for_model = new_placeholder_dict(train)
for k in self.embeddings.keys():
batch_for_model["{}:0".format(k)] = batch_dict[k]
# Allow us to track a length, which is needed for BLSTMs
if self.lengths_key is not None:
batch_for_model[self.lengths] = batch_dict[self.lengths_key]
if y is not None:
batch_for_model[self.y] = fill_y(len(self.labels), y)
else:
SET_TRAIN_FLAG(train)
batch_for_model = {}
for k in self.embeddings.keys():
batch_for_model[k] = batch_dict[k]
# Allow us to track a length, which is needed for BLSTMs
if self.lengths_key is not None:
batch_for_model["lengths"] = batch_dict[self.lengths_key]
return batch_for_model
def make_input(self, batch_dict, train=False):
if train is False:
return self.inference.make_input(batch_dict)
y = batch_dict.get('y', None)
feed_dict = new_placeholder_dict(True)
for key in self.parallel_params.keys():
feed_dict["{}_parallel:0".format(key)] = batch_dict[key]
# Allow us to track a length, which is needed for BLSTMs
if self.lengths_key is not None:
feed_dict[self.lengths] = batch_dict[self.lengths_key]
if y is not None:
feed_dict[self.y] = fill_y(len(self.labels), y)
return feed_dict
def make_input(self, batch_dict, train=False):
if train is False:
return self.inference.make_input(batch_dict)
y = batch_dict.get('y', None)
feed_dict = new_placeholder_dict(True)
for key in self.parallel_params.keys():
feed_dict["{}_parallel:0".format(key)] = batch_dict[key]
# Allow us to track a length, which is needed for BLSTMs
if self.lengths_key is not None:
feed_dict[self.lengths] = batch_dict[self.lengths_key]
if y is not None:
feed_dict[self.y] = fill_y(len(self.labels), y)
return feed_dict
def make_input(self, batch_dict, train=False):
"""Transform a `batch_dict` into a TensorFlow `feed_dict`
:param batch_dict: (``dict``) A dictionary containing all inputs to the embeddings for this model
:param train: (``bool``) Are we training. Defaults to False
:return:
"""
y = batch_dict.get('y', None)
feed_dict = new_placeholder_dict(train)
for k in self.embeddings.keys():
feed_dict["{}:0".format(k)] = batch_dict[k]
# Allow us to track a length, which is needed for BLSTMs
if self.lengths_key is not None:
feed_dict[self.lengths] = batch_dict[self.lengths_key]
if y is not None:
feed_dict[self.y] = fill_y(len(self.labels), y)
return feed_dict
def make_input(self, batch_dict):
feed_dict = new_placeholder_dict(False)
for k in self.embeddings.keys():
feed_dict["{}:0".format(k)] = batch_dict[k]
return feed_dict