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)

Pooling layer

Parameters

widthint

Specifies the width of the pooling window.

heightint

Specifies the height of the pooling window.

namestring, optional

Specifies the name of the layer.

strideint, optional

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

stride_horizontalint, optional

Specifies the step size of the moving window horizontally.

stride_verticalint, optional

Specifies the step size of the moving window vertically.

paddingint, optional

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

padding_widthint, optional

Specifies the length of the padding horizontally.

padding_heightint, optional

Specifies the length of the padding vertically.

poolstring, optional

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

dropoutfloat, optional

Specifies the dropout rate.

src_layersiter-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

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