layer_to_dense_stereo_and_diff: Split Model into Two Parallel Layers

In tpq/caress: Caress, a Gentler Introduction to Keras

Description

This function splits the input into three parallel layers. The first two layers have the same architecture, but are influenced by different weights. The third layer is the difference of the other two layers.

Usage

layer_to_dense_stereo_and_diff(
  object,
  units,
  activation = NULL,
  name = NULL,
  ...
)

Arguments

object	A keras model.
units	Arguments passed to keras::layer_dense.
activation	Arguments passed to keras::layer_dense.
name	A string. The prefix label for all layers.
...	Arguments passed to keras::layer_dense.

Value

A list of three layers: Channel 1, Channel 2, and Channel 1 & Channel 2.

tpq/caress documentation built on March 11, 2021, 8:03 p.m.