def _construct_layers(self):
self.input_layer = Input(shape=(self.n_objects_fit_,
self.n_object_features_fit_))
# Todo: Variable sized input
# X = Input(shape=(None, n_features))
logger.info("n_hidden {}, n_units {}".format(self.n_hidden,
self.n_units))
hidden_dense_kwargs = {
"kernel_regularizer": self.kernel_regularizer_,
"kernel_initializer": self.kernel_initializer,
"activation": self.activation,
}
hidden_dense_kwargs.update(
self._get_prefix_attributes("hidden_dense_layer__"))
if self.batch_normalization:
if self.add_zeroth_order_model:
self.hidden_layers_zeroth = [
NormalizedDense(
self.n_units,
name="hidden_zeroth_{}".format(x),
**hidden_dense_kwargs,
) for x in range(self.n_hidden)
]
self.hidden_layers = [
NormalizedDense(self.n_units,
name="hidden_{}".format(x),
**hidden_dense_kwargs)
for x in range(self.n_hidden)
]
else:
if self.add_zeroth_order_model:
self.hidden_layers_zeroth = [
Dense(
self.n_units,
name="hidden_zeroth_{}".format(x),
**hidden_dense_kwargs,
) for x in range(self.n_hidden)
]
self.hidden_layers = [
Dense(self.n_units,
name="hidden_{}".format(x),
**hidden_dense_kwargs) for x in range(self.n_hidden)
]
assert len(self.hidden_layers) == self.n_hidden
self.output_node = Dense(1,
activation="sigmoid",
kernel_regularizer=self.kernel_regularizer_)
if self.add_zeroth_order_model:
self.output_node_zeroth = Dense(
1,
activation="sigmoid",
kernel_regularizer=self.kernel_regularizer_)
def _construct_layers(self, **kwargs):
self.input_layer = Input(shape=(self.n_objects,
self.n_object_features))
# Todo: Variable sized input
# X = Input(shape=(None, n_features))
if self.batch_normalization:
if self._use_zeroth_model:
self.hidden_layers_zeroth = [
NormalizedDense(self.n_units,
name="hidden_zeroth_{}".format(x),
*kwargs) for x in range(self.n_hidden)
]
self.hidden_layers = [
NormalizedDense(self.n_units,
name="hidden_{}".format(x),
**kwargs) for x in range(self.n_hidden)
]
else:
if self._use_zeroth_model:
self.hidden_layers_zeroth = [
Dense(self.n_units,
name="hidden_zeroth_{}".format(x),
**kwargs) for x in range(self.n_hidden)
]
self.hidden_layers = [
Dense(self.n_units, name="hidden_{}".format(x), **kwargs)
for x in range(self.n_hidden)
]
assert len(self.hidden_layers) == self.n_hidden
self.output_node = Dense(
1,
activation="linear",
kernel_regularizer=self.kernel_regularizer,
name="score",
)
if self._use_zeroth_model:
self.output_node_zeroth = Dense(
1,
activation="linear",
kernel_regularizer=self.kernel_regularizer,
name="zero_score",
)
self.weighted_sum = Dense(
1,
activation="sigmoid",
kernel_regularizer=self.kernel_regularizer,
name="weighted_sum",
)
def _construct_layers(self):
logger.info("n_hidden {}, n_units {}".format(self.n_hidden,
self.n_units))
self.x1 = Input(shape=(self.n_object_features_fit_, ))
self.x2 = Input(shape=(self.n_object_features_fit_, ))
self.output_node = Dense(1,
activation="sigmoid",
kernel_regularizer=self.kernel_regularizer_)
self.output_layer_score = Dense(1, activation="linear")
hidden_dense_kwargs = {
"kernel_regularizer": self.kernel_regularizer_,
"kernel_initializer": self.kernel_initializer,
"activation": self.activation,
}
hidden_dense_kwargs.update(
self._get_prefix_attributes("hidden_dense_layer__"))
if self.batch_normalization:
self.hidden_layers = [
NormalizedDense(self.n_units,
name="hidden_{}".format(x),
**hidden_dense_kwargs)
for x in range(self.n_hidden)
]
else:
self.hidden_layers = [
Dense(self.n_units,
name="hidden_{}".format(x),
**hidden_dense_kwargs) for x in range(self.n_hidden)
]
assert len(self.hidden_layers) == self.n_hidden
def _construct_layers(self, n_hidden=2, n_units=16, **kwargs):
self.input_layer = Input(shape=(self.n_objects, self.n_features))
# Todo: Variable sized input
# X = Input(shape=(None, n_features))
if self.batch_normalization:
if self._use_zeroth_model:
self.hidden_layers_zeroth = [
NormalizedDense(n_units,
name="hidden_zeroth_{}".format(x),
kernel_regularizer=self.kernel_regularizer,
activation=self.non_linearities)
for x in range(n_hidden)
]
self.hidden_layers = [
NormalizedDense(n_units,
name="hidden_{}".format(x),
kernel_regularizer=self.kernel_regularizer,
activation=self.non_linearities)
for x in range(n_hidden)
]
else:
if self._use_zeroth_model:
self.hidden_layers_zeroth = [
Dense(n_units,
name="hidden_zeroth_{}".format(x),
kernel_regularizer=self.kernel_regularizer,
activation=self.non_linearities)
for x in range(n_hidden)
]
self.hidden_layers = [
Dense(n_units,
name="hidden_{}".format(x),
kernel_regularizer=self.kernel_regularizer,
activation=self.non_linearities) for x in range(n_hidden)
]
assert len(self.hidden_layers) == n_hidden
self.output_node = Dense(1,
activation='sigmoid',
kernel_regularizer=self.kernel_regularizer)
if self._use_zeroth_model:
self.output_node_zeroth = Dense(
1,
activation='sigmoid',
kernel_regularizer=self.kernel_regularizer)
def _construct_layers(self, **kwargs):
self.output_node = Dense(1, activation='sigmoid', kernel_regularizer=self.kernel_regularizer)
self.x1 = Input(shape=(self.n_object_features,))
self.x2 = Input(shape=(self.n_object_features,))
if self.batch_normalization:
self.hidden_layers = [NormalizedDense(self.n_units, name="hidden_{}".format(x), **kwargs) for x in
range(self.n_hidden)]
else:
self.hidden_layers = [Dense(self.n_units, name="hidden_{}".format(x), **kwargs) for x in
range(self.n_hidden)]
assert len(self.hidden_layers) == self.n_hidden
def _construct_layers(self, **kwargs):
self.input_layer = Input(shape=(self.n_top, self.n_object_features))
self.output_node = Dense(1,
activation="linear",
kernel_regularizer=self.kernel_regularizer)
if self.batch_normalization:
self.hidden_layers = [
NormalizedDense(self.n_units,
name="hidden_{}".format(x),
kernel_regularizer=self.kernel_regularizer,
kernel_initializer=self.kernel_initializer,
activation=self.non_linearities,
**kwargs) for x in range(self.n_hidden)
]
else:
self.hidden_layers = [
Dense(self.n_units,
name="hidden_{}".format(x),
kernel_regularizer=self.kernel_regularizer,
kernel_initializer=self.kernel_initializer,
activation=self.non_linearities,
**kwargs) for x in range(self.n_hidden)
]
assert len(self.hidden_layers) == self.n_hidden
