mlx.nn.MaxPool2d#

class MaxPool2d(kernel_size: int | Tuple[int, int], stride: int | Tuple[int, int] | None = None, padding: int | Tuple[int, int] | None = 0)#

Applies 2-dimensional max pooling.

Assuming an input of shape \((N, H, W, C)\) and kernel_size is \((k_H, k_W)\), the output is a tensor of shape \((N, H_{out}, W_{out}, C)\), given by:

\[\begin{split}\begin{aligned} \text{out}(N_i, h, w, C_j) = & \max_{m=0, \ldots, k_H-1} \max_{n=0, \ldots, k_W-1} \\ & \text{input}(N_i, \text{stride[0]} \times h + m, \text{stride[1]} \times w + n, C_j), \end{aligned}\end{split}\]

where \(H_{out} = \left\lfloor\frac{H + 2 * \text{padding[0]} - \text{kernel\_size[0]}}{\text{stride[0]}}\right\rfloor + 1\), \(W_{out} = \left\lfloor\frac{W + 2 * \text{padding[1]} - \text{kernel\_size[1]}}{\text{stride[1]}}\right\rfloor + 1\).

The parameters kernel_size, stride, padding, can either be:

  • a single int – in which case the same value is used for both the height and width axis;

  • a tuple of two int s – in which case, the first int is used for the height axis, the second int for the width axis.

Parameters:

  • kernel_size (int or tuple(int, int)) – The size of the pooling window.

  • stride (int or tuple(int, int), optional) – The stride of the pooling window. Default: kernel_size.

  • padding (int or tuple(int, int), optional) – How much negative infinity padding to apply to the input. The padding is applied on both sides of the height and width axis. Default: 0.

Examples

>>> import mlx.core as mx
>>> import mlx.nn.layers as nn
>>> x = mx.random.normal(shape=(8, 32, 32, 4))
>>> pool = nn.MaxPool2d(kernel_size=2, stride=2)
>>> pool(x)

Methods