layer_variable {tfprobability} | R Documentation |
Variable Layer
Description
Simply returns a (trainable) variable, regardless of input.
This layer implements the mathematical function f(x) = c
where c
is a
constant, i.e., unchanged for all x
. Like other Keras layers, the constant
is trainable
. This layer can also be interpretted as the special case of
layer_dense()
when the kernel
is forced to be the zero matrix
(tf$zeros
).
Usage
layer_variable(
object,
shape,
dtype = NULL,
activation = NULL,
initializer = "zeros",
regularizer = NULL,
constraint = NULL,
...
)
Arguments
object |
What to compose the new
|
shape |
integer or integer vector specifying the shape of the output of this layer. |
dtype |
TensorFlow |
activation |
An activation function. See |
initializer |
Initializer for the |
regularizer |
Regularizer function applied to the |
constraint |
Constraint function applied to the |
... |
Additional keyword arguments passed to the |
Value
a Keras layer
See Also
Other layers:
layer_autoregressive()
,
layer_conv_1d_flipout()
,
layer_conv_1d_reparameterization()
,
layer_conv_2d_flipout()
,
layer_conv_2d_reparameterization()
,
layer_conv_3d_flipout()
,
layer_conv_3d_reparameterization()
,
layer_dense_flipout()
,
layer_dense_local_reparameterization()
,
layer_dense_reparameterization()
,
layer_dense_variational()