dlpy.layers.ROIPooling

class dlpy.layers.ROIPooling(name=None, act='AUTO', output_height=7, output_width=7, spatial_scale=0.0625, src_layers=None, **kwargs)

ROIPooling layer

Parameters

namestring, optional

Specifies the name of the layer.

actstring, optional

Specifies the activation function. Valid Values: AUTO, IDENTITY, Default: AUTO

output_heightint, optional

Specifies the output height of the region pooling layer. Default: 7

output_widthint, optional

Specifies the output width of the region pooling layer. Default: 7

spatial_scalefloat, optional

Specifies the spatial scale of ROIs coordinates (in the input image space) in related to the feature map pixel space. Default: 0.0625

src_layersiter-of-Layers, optional

Specifies the layers directed to this layer.

Returns

ROIPooling

__init__(name=None, act='AUTO', output_height=7, output_width=7, spatial_scale=0.0625, src_layers=None, **kwargs)

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

Methods

__init__([name, act, output_height, …])	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