dlpy.layers.FCMPLayer¶
-
class
dlpy.layers.
FCMPLayer
(width, height, depth, n_weights, forward_func, backward_func, name=None, src_layers=None, **kwargs)¶ FCMP layer
- Parameters
- widthint
Specifies the width of feature maps for this layer.
- heightint
Specifies the height of feature maps for this layer.
- depthint
Specifies the depth of feature maps for this layer.
- n_weightsint
Specifies the number of weights used in the FCMP layer.
- forward_funcstring
specifies the custom function for the FCMP layer’s forward pass.
- backward_funcstring
Specifies the custom function for the FCMP layer’s backward pass.
- namestring, optional
Specifies the name of the layer.
- src_layersiter-of-Layers, optional
Specifies the layers directed to this layer.
- Returns
-
__init__
(width, height, depth, n_weights, forward_func, backward_func, name=None, src_layers=None, **kwargs)¶ Initialize self. See help(type(self)) for accurate signature.
Methods
__init__
(width, height, depth, n_weights, …)Initialize self.
count_instances
()format_name
([block_num, local_count])Format the name of the layer
get_number_of_instances
()to_model_params
()Convert the model configuration to CAS action parameters
Attributes
can_be_last_layer
kernel_size
layer_id
num_bias
num_weights
number_of_instances
output_size
rnn_summary
Return a DataFrame containing the layer information for rnn models
summary
Return a DataFrame containing the layer information
type
type_desc
type_label