keraflow.layers.convolution.Pooling3D Class Reference

Zero-padding layer for (input_depth, input_x, input_y, input_z) inputs. More...

Inheritance diagram for keraflow.layers.convolution.Pooling3D:

Public Member Functions
def	__init__
Public Member Functions inherited from keraflow.layers.convolution.PoolingBase
def	__init__

Detailed Description

Zero-padding layer for (input_depth, input_x, input_y, input_z) inputs.

• input_shape: 5D, (nb_samples, input_depth, input_x, input_y, input_z)
• output_shape: 5D, (nb_samples, input_depth, output_x, output_y, output_z)

Note

output_x, output_y and output_z are determined by pad and strides. For details, please see PoolingBase, ConvolutionBase.

Constructor & Destructor Documentation

def keraflow.layers.convolution.Pooling3D.__init__	(		self,
			mode,
			pool_size = (2, 2,
			strides = None,
			pad = 'valid',
			kwargs
	)

Parameters

mode	str. 'max' or 'avg' for max and average pooling respectively.
pool_size	tuple of int. Shape of the pooling window.
strides	tuple of int. Steps for sliding the pooling window.
pad	str, 'valid' of 'same'. See PoolingBase, ConvolutionBase.
kwargs	see Layer.__init__.