theanets.layers.feedforward.Classifier

class theanets.layers.feedforward.Classifier(**kwargs)

A classifier layer performs a softmax over a linear input transform.

Classifier layers are typically the “output” layer of a classifier network.

This layer type really only wraps the output activation of a standard Feedforward layer.

Notes

The classifier layer is just a vanilla Feedforward layer that uses a 'softmax' output activation.

__init__(**kwargs)

Methods

__init__(**kwargs)
setup()	Set up the parameters and initial values for this layer.
transform(inputs)	Transform the inputs for this layer into an output for the layer.

Attributes

input_size	For networks with one input, get the input size.
num_params	Total number of learnable parameters in this layer.
params	A list of all parameters in this layer.