theanets.layers.base.Input¶
-
class
theanets.layers.base.
Input
(name='in', ndim=2, sparse=False, **kwargs)[source]¶ A layer that receives external input data.
Input layers are responsible for the Theano variables that represent input to a network. The name of the layer is passed along to the symbolic Theano input variable.
Input layers essentially add only noise to the input data (if desired), but otherwise reproduce their inputs exactly.
Parameters: - ndim : int, optional
Number of dimensions required to store the input data for this layer. If a
shape
tuple is given, this defaults to1 + len(shape)
; otherwise, this defaults to 2, i.e.,(num-examples, num-variables)
.- sparse : bool or str, optional
If this is
'csr'
or'csc'
, then the inputs to the loss will be stored as sparse matrices in the CSR or CSC format (respectively). If this is True, sparse input will be enabled in CSR format. By default this is False, which means inputs are dense.
Raises: - AssertionError :
If
sparse
is enabled andndim
is not 2.
-
__init__
(name='in', ndim=2, sparse=False, **kwargs)[source]¶ x.__init__(…) initializes x; see help(type(x)) for signature
Methods
__init__
([name, ndim, sparse])x.__init__(…) initializes x; see help(type(x)) for signature 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. bind
(graph[, reset, initialize])Bind this layer into a computation graph. connect
(inputs)Create Theano variables representing the outputs of this layer. find
(key)Get a shared variable for a parameter by name. full_name
(name)Return a fully-scoped name for the given layer output. log
()Log some information about this layer. log_params
()Log information about this layer’s parameters. resolve_inputs
(layers)Resolve the names of inputs for this layer into shape tuples. resolve_outputs
()Resolve the names of outputs for this layer into shape tuples. 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_name
Name of layer input (for layers with one input). input_shape
Shape of layer input (for layers with one input). input_size
Size of layer input (for layers with one input). output_name
Full name of the default output for this layer. output_shape
Shape of default output from this layer. output_size
Number of “neurons” in this layer’s default output. params
A list of all parameters in this layer. -
resolve_inputs
(layers)[source]¶ Resolve the names of inputs for this layer into shape tuples.
Parameters: - layers : list of
Layer
A list of the layers that are available for resolving inputs.
Raises: - theanets.util.ConfigurationError :
If an input cannot be resolved.
- layers : list of
-
transform
(inputs)[source]¶ Transform the inputs for this layer into an output for the layer.
Parameters: - inputs : dict of Theano expressions
Symbolic inputs to this layer, given as a dictionary mapping string names to Theano expressions. See
Layer.connect()
.
Returns: - output : Theano expression
The output for this layer is the same as the input.
- updates : list
An empty updates list.