def build(self, input_shape):
shape = [self.maximum_position + 1, input_shape.as_list()[-1]]
initializer = tf.keras.initializers.glorot_uniform()
self.embedding = tf.Variable(
initial_value=lambda: initializer(shape, dtype=self.dtype),
name=compat.name_from_variable_scope("position_encoding/w_embs"))
super(PositionEmbedder, self).build(input_shape)
def build(self, i, dtype=tf.float32):
shape = [self.maximum_position + 1, 4]
initializer = tf.keras.initializers.glorot_uniform()
self.embedding = tf.Variable(
initial_value=lambda: initializer(shape, dtype=dtype),
name=compat.name_from_variable_scope("position_encoding/w_embs/" +
str(i)))
def build(self, input_shape=None):
if self.embedding_file:
pretrained = load_pretrained_embeddings(
self.embedding_file,
self.vocabulary_file,
num_oov_buckets=self.num_oov_buckets,
with_header=self.embedding_file_with_header,
case_insensitive_embeddings=self.case_insensitive_embeddings)
self.embedding_size = pretrained.shape[-1]
initializer = tf.constant_initializer(
value=pretrained.astype(self.dtype))
else:
initializer = None
shape = [self.vocabulary_size, self.embedding_size]
if compat.is_tf2():
self.embedding = self.add_variable(
name=compat.name_from_variable_scope("w_embs"),
shape=shape,
initializer=initializer,
trainable=self.trainable)
else:
self.embedding = tf.get_variable("w_embs",
shape=shape,
dtype=self.dtype,
initializer=initializer,
trainable=self.trainable)
super(WordEmbedder, self).build(input_shape)
def build(self, input_shape=None):
shape = [self.vocabulary_size, self.embedding_size]
initializer = tf.keras.initializers.glorot_uniform()
self.embedding = tf.Variable(
initial_value=lambda: initializer(shape, dtype=self.dtype),
name=compat.name_from_variable_scope("w_char_embs"))
super(CharEmbedder, self).build(input_shape)
def build(self, input_shape):
decoder_shape = input_shape[1]
self.decoder_state_sizes = [
shape.as_list()[-1] for shape in compat.nest.flatten(decoder_shape)
]
self.linear = tf.keras.layers.Dense(
sum(self.decoder_state_sizes),
activation=self.activation,
name=compat.name_from_variable_scope("dense"))
def build(self, input_shape=None):
shape = [self.vocabulary_size, self.embedding_size]
if compat.is_tf2():
self.embedding = self.add_variable(
name=compat.name_from_variable_scope("w_char_embs"),
shape=shape)
else:
self.embedding = tf.get_variable("w_char_embs",
shape=shape,
dtype=self.dtype)
super(CharEmbedder, self).build(input_shape)
def build(self, input_shape=None):
if self.embedding_file:
pretrained = load_pretrained_embeddings(
self.embedding_file,
self.vocabulary_file,
num_oov_buckets=self.num_oov_buckets,
with_header=self.embedding_file_with_header,
case_insensitive_embeddings=self.case_insensitive_embeddings)
self.embedding_size = pretrained.shape[-1]
initializer = tf.constant_initializer(value=pretrained.astype(self.dtype))
else:
initializer = tf.keras.initializers.glorot_uniform()
shape = [self.vocabulary_size, self.embedding_size]
self.embedding = tf.Variable(
initial_value=lambda: initializer(shape, dtype=self.dtype),
trainable=self.trainable,
name=compat.name_from_variable_scope("w_embs"))
super(WordEmbedder, self).build(input_shape)
