MinPool

Contents

MinPool#

class brainpy.dnn.MinPool(kernel_size, stride=1, padding='VALID', channel_axis=None, mode=None, name=None)[source]#

Pools the input by taking the minimum over a window.

Parameters:

  • kernel_size (Union[int, Sequence[int]]) – An integer, or a sequence of integers defining the window to reduce over.

  • stride (Union[int, Sequence[int]]) – An integer, or a sequence of integers, representing the inter-window stride (default: (1, …, 1)).

  • padding (Union[str, Sequence[Tuple[int, int]]]) – Either the string ‘SAME’, the string ‘VALID’, or a sequence of n (low, high) integer pairs that give the padding to apply before and after each spatial dimension.

  • channel_axis (Optional[int]) – Axis of the spatial channels for which pooling is skipped, used to infer kernel_size or stride if they are an integer.

  • mode (Mode) – The computation mode.

  • name (Optional[str]) – The object name.

Contents