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)add_bias
(name, size[, mean, std])Helper method to create a new bias vector. add_weights
(name, nin, nout[, mean, std, ...])Helper method to create a new weight matrix. connect
(inputs)Create Theano variables representing the outputs of this layer. find
(key)Get a shared variable for a parameter by name. log
()Log some information about this layer. output_name
([name])Return a fully-scoped name for the given layer output. setup
()Set up the parameters and initial values for this layer. to_spec
()Create a specification dictionary 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. -