Layer base classes

class lasagne.layers.Layer(incoming, name=None)

The Layer class represents a single layer of a neural network. It should be subclassed when implementing new types of layers.

Because each layer can keep track of the layer(s) feeding into it, a network’s output Layer instance can double as a handle to the full network.

add_param(spec, shape, name=None, **tags)

Register and initialize a Theano shared variable containing parameters associated with the layer.

When defining a new layer, this method can be used in the constructor to define which parameters the layer has, what their shapes are, how they should be initialized and what tags are associated with them.

All parameter variables associated with the layer can be retrieved using Layer.get_params().

Parameters:

spec : Theano shared variable, numpy array or callable

an initializer for this parameter variable. This should initialize the variable with an array of the specified shape. See lasagne.utils.create_param() for more information.

shape : tuple of int

a tuple of integers representing the desired shape of the parameter array.

name : str (optional)

the name of the parameter variable. This will be passed to theano.shared when the variable is created. If spec is already a shared variable, this parameter will be ignored to avoid overwriting an existing name. If the layer itself has a name, the name of the parameter variable will be prefixed with it and it will be of the form ‘layer_name.param_name’.

**tags (optional)

tags associated with the parameter variable can be specified as keyword arguments.

To associate the tag tag1 with the variable, pass tag1=True.

By default, the tags regularizable and trainable are associated with the parameter variable. Pass regularizable=False or trainable=False respectively to prevent this.

Returns:

Theano shared variable

the resulting parameter variable

Notes

It is recommend to assign the resulting parameter variable to an attribute of the layer, so it can be accessed easily, for example:

>>> self.W = self.add_param(W, (2, 3), name='W')  

get_output_for(input, **kwargs)

Propagates the given input through this layer (and only this layer).

Parameters:

input : Theano expression

The expression to propagate through this layer.

Returns:

output : Theano expression

The output of this layer given the input to this layer.

Notes

This is called by the base lasagne.layers.get_output() to propagate data through a network.

This method should be overridden when implementing a new Layer class. By default it raises NotImplementedError.

get_output_shape_for(input_shape)

Computes the output shape of this layer, given an input shape.

Parameters:

input_shape : tuple

A tuple representing the shape of the input. The tuple should have as many elements as there are input dimensions, and the elements should be integers or None.

Returns:

tuple

A tuple representing the shape of the output of this layer. The tuple has as many elements as there are output dimensions, and the elements are all either integers or None.

Notes

This method will typically be overridden when implementing a new Layer class. By default it simply returns the input shape. This means that a layer that does not modify the shape (e.g. because it applies an elementwise operation) does not need to override this method.

get_params(**tags)

Returns a list of all the Theano variables that parameterize the layer.

By default, all parameters that participate in the forward pass will be returned (in the order they were registered in the Layer’s constructor via add_param()). The list can optionally be filtered by specifying tags as keyword arguments. For example, trainable=True will only return trainable parameters, and regularizable=True will only return parameters that can be regularized (e.g., by L2 decay).

Parameters:

**tags (optional)

tags can be specified to filter the list. Specifying tag1=True will limit the list to parameters that are tagged with tag1. Specifying tag1=False will limit the list to parameters that are not tagged with tag1. Commonly used tags are regularizable and trainable.

Returns:

list of Theano shared variables

A list of variables that parameterize the layer

Notes

For layers without any parameters, this will return an empty list.

class lasagne.layers.MergeLayer(incomings, name=None)

This class represents a layer that aggregates input from multiple layers. It should be subclassed when implementing new types of layers that obtain their input from multiple layers.

get_output_for(inputs, **kwargs)

Propagates the given inputs through this layer (and only this layer).

Parameters:

inputs : list of Theano expressions

The Theano expressions to propagate through this layer.

Returns:

Theano expressions

The output of this layer given the inputs to this layer.

Notes

This is called by the base lasagne.layers.get_output() to propagate data through a network.

This method should be overridden when implementing a new Layer class with multiple inputs. By default it raises NotImplementedError.

get_output_shape_for(input_shapes)

Computes the output shape of this layer, given a list of input shapes.

Parameters:

input_shape : list of tuple

A list of tuples, with each tuple representing the shape of one of the inputs (in the correct order). These tuples should have as many elements as there are input dimensions, and the elements should be integers or None.

Returns:

tuple

A tuple representing the shape of the output of this layer. The tuple has as many elements as there are output dimensions, and the elements are all either integers or None.

Notes

This method must be overridden when implementing a new Layer class with multiple inputs. By default it raises NotImplementedError.