dlpy.layers.Pooling

class dlpy.layers.Pooling(width=None, height=None, stride=None, name=None, stride_horizontal=None, stride_vertical=None, padding=None, padding_width=None, padding_height=None, pool='max', dropout=None, src_layers=None, **kwargs)

Bases: dlpy.layers.Layer

Pooling layer

Parameters:
width : int

Specifies the width of the pooling window.

height : int

Specifies the height of the pooling window.

name : string, optional

Specifies the name of the layer.

stride : int, optional

Specifies the step size of the moving window, assuming a equal moves vertically and horizontally

stride_horizontal : int, optional

Specifies the step size of the moving window horizontally.

stride_vertical : int, optional

Specifies the step size of the moving window vertically.

padding : int, optional

Specifies the length of the padding assuming equal padding horizontally and vertically.

padding_width : int, optional

Specifies the length of the padding horizontally.

padding_height : int, optional

Specifies the length of the padding vertically.

pool : string, optional

Specifies the type of the pooling layer.
Valid Values: MAX, MIN, MEAN, AVERAGE, FIXED, RANDOM, MEDIAN
Default: MAX

dropout : float, optional

Specifies the dropout rate.

src_layers : iter-of-Layers, optional

Specifies the layers directed to this layer.

Returns:
Pooling
__init__(width=None, height=None, stride=None, name=None, stride_horizontal=None, stride_vertical=None, padding=None, padding_width=None, padding_height=None, pool='max', dropout=None, src_layers=None, **kwargs)

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__([width, height, stride, name, …]) 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