Skip to content

RowwiseMult

latent.layers.RowwiseMult

Performs row-wise multiplication between input vectors.

__init__(self, name=None) special

Parameters:

Name Type Description Default
name str

String indicating the name of the layer.

None

call(self, inputs)

This is where the layer's logic lives.

Note here that call() method in tf.keras is little bit different from keras API. In keras API, you can pass support masking for layers as additional arguments. Whereas tf.keras has compute_mask() method to support masking.

Parameters:

Name Type Description Default
inputs

Input tensor, or list/tuple of input tensors.

required
**kwargs

Additional keyword arguments. Currently unused.

required

Returns:

Type Description

A tensor or list/tuple of tensors.