MaxPool1d

Contents

MaxPool1d#

class brainstate.nn.MaxPool1d(kernel_size, stride=None, padding='VALID', channel_axis=-1, return_indices=False, name=None, in_size=None)#

Applies a 1D max pooling over an input signal composed of several input planes.

In the simplest case, the output value of the layer with input size \((N, L, C)\) and output \((N, L_{out}, C)\) can be precisely described as:

\[out(N_i, k, C_j) = \max_{m=0, \ldots, \text{kernel\_size} - 1} input(N_i, stride \times k + m, C_j)\]

If padding is non-zero, then the input is implicitly padded with negative infinity on both sides for padding number of points. This link has a nice visualization of the pooling parameters.

Shape:

  • Input: \((N, L_{in}, C)\) or \((L_{in}, C)\).

  • Output: \((N, L_{out}, C)\) or \((L_{out}, C)\), where

    \[L_{out} = \left\lfloor \frac{L_{in} + 2 \times \text{padding} - \text{kernel\_size}}{\text{stride}} + 1\right\rfloor\]
Parameters:

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

  • stride (int | Sequence[int]) – An integer, or a sequence of integers, representing the inter-window stride. Default: kernel_size

  • padding (str | int | Tuple[int, ...] | 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. Default: ‘VALID’

  • channel_axis (int | None) – Axis of the spatial channels for which pooling is skipped. If None, there is no channel axis. Default: -1

  • return_indices (bool) – If True, will return the max indices along with the outputs. Useful for MaxUnpool1d. Default: False

  • name (str | None) – The object name.

  • in_size (int | Sequence[int] | integer | Sequence[integer] | None) – The shape of the input tensor.

Examples

>>> import brainstate
>>> # pool of size=3, stride=2
>>> m = MaxPool1d(3, stride=2, channel_axis=-1)
>>> input = brainstate.random.randn(20, 50, 16)
>>> output = m(input)
>>> output.shape
(20, 24, 16)
Contents