keraflow.layers.convolution.Pooling1D Class Reference

Pooling layer for sub-sampling (sequence_length, input_dim) inputs. More...

Inheritance diagram for keraflow.layers.convolution.Pooling1D:

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

Detailed Description

Pooling layer for sub-sampling (sequence_length, input_dim) inputs.

• input_shape: 3D, (nb_samples, sequence_length, input_dim)
• output_shape: 3D, (nb_samples, output_sequence_length, input_dim)

Note

output_sequence_length is determined by pad and stride. For details, please see PoolingBase, ConvolutionBase.

Constructor & Destructor Documentation

def keraflow.layers.convolution.Pooling1D.__init__	(		self,
			mode,
			pool_length = 2,
			stride = None,
			pad = 'valid',
			kwargs
	)

Parameters

mode	str. 'max' or 'avg' for max and average pooling respectively.
pool_length	int. The height of the pooling window. The width of the window will always be the input's width.
stride	int. Steps for vertically sliding the pooling window.
pad	str, 'valid' of 'same'. See PoolingBase, ConvolutionBase.
kwargs	see Layer.__init__.