Pooling

BasePool

class paddle.v2.pooling.BasePool(name)

Base Pooling Type. Note these pooling types are used for sequence input, not for images. Each PoolingType contains one parameter:

Parameters:name (basestring) – pooling layer type name used by paddle.

Avg

class paddle.v2.pooling.Avg(strategy='average')

Average pooling.

Return the average values for each dimension in sequence or time steps.

\[sum(samples\_of\_a\_sequence)/sample\_num\]

Max

class paddle.v2.pooling.Max(output_max_index=None)

Max pooling.

Return the very large values for each dimension in sequence or time steps.

\[max(samples\_of\_a\_sequence)\]
Parameters:output_max_index (bool|None) – True if output sequence max index instead of max value. None means use default value in proto.

Sum

class paddle.v2.pooling.Sum

Sum pooling.

Return the sum values of each dimension in sequence or time steps.

\[sum(samples\_of\_a\_sequence)\]

SquareRootN

class paddle.v2.pooling.SquareRootN

Square Root Pooling.

Return the square root values of each dimension in sequence or time steps.

\[sum(samples\_of\_a\_sequence)/sqrt(sample\_num)\]

CudnnAvg

class paddle.v2.pooling.CudnnAvg

Cudnn average pooling only support GPU. Return the average value in the pooling window.

CudnnMax

class paddle.v2.pooling.CudnnMax

Cudnn max pooling only support GPU. Return the maxinum value in the pooling window.