smash.factory.Net.add_scale#

Net.add_scale(bounds)[source]#

Add a scaling layer that applies the min-max scaling function to the outputs.

Parameters:
boundsListLike

A sequence of (min, max) values that the outputs will be scaled to.

Examples

>>> from smash.factory import Net
>>> net = Net()
>>> net.add_dense(2, input_shape=8, activation="sigmoid")
>>> net.add_scale([(2,3), (5,6)])
>>> net
+----------------------------------------------------------+
| Layer Type            Input/Output Shape  Num Parameters |
+----------------------------------------------------------+
| Dense                 (8,)/(2,)           18             |
| Activation (Sigmoid)  (2,)/(2,)           0              |
| Scale (MinMaxScale)   (2,)/(2,)           0              |
+----------------------------------------------------------+
Total parameters: 18
Trainable parameters: 18