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.
\[sum(samples\_of\_a\_sequence)/sqrt(sample\_num)\]
CudnnMax¶
-
class
paddle.v2.pooling.CudnnMax Cudnn max pooling only support GPU. Return the maxinum value in the pooling window.