nip.utils.torch.MaxPool2dSimulateBatchDims

nip.utils.torch.MaxPool2dSimulateBatchDims#

class nip.utils.torch.MaxPool2dSimulateBatchDims(kernel_size: int | Tuple[int, ...], stride: int | Tuple[int, ...] | None = None, padding: int | Tuple[int, ...] = 0, dilation: int | Tuple[int, ...] = 1, return_indices: bool = False, ceil_mode: bool = False)[source]#

2D max pool layer with arbitrary batch dimensions.

See torch.nn.MaxPool2d for documentation.

Assumes an input of shape (… channels height width).

Methods Summary

forward(x)

Apply the module to the input tensor, simulating multiple batch dimensions.

Attributes

T_destination

call_super_init

dump_patches

feature_dims

kernel_size

stride

padding

dilation

return_indices

ceil_mode

training

Methods

forward(x: Tensor) Tensor[source]#

Apply the module to the input tensor, simulating multiple batch dimensions.

Parameters:

x (Tensor) – The input tensor.

Returns:

out (Tensor) – The output tensor after applying the module.