View source on GitHub |
Affine layer.
tfp.experimental.joint_distribution_layers.AffineLayer(
weights, bias
)
This represents a linear map: y = weights @ x + bias
.
Attributes | |
---|---|
weights
|
A floating point Tensor with shape [out_units, in_units] .
|
bias
|
A floating point Tensor with shape [out_units] .
|
Methods
__call__
__call__(
x
)
Applies the layer to an input.
Args | |
---|---|
x
|
A floating point Tensor with shape [in_units]. |
Returns | |
---|---|
y
|
A floating point Tensor with shape [out_units]. |