models.modules.Pool

class Pool(type: str, kernel_size: int = 2, stride: int | None = None)

Bases: LayerGen

Pooling layer generator

Uses modules torch.nn.AvgPool2d, torch.nn.MaxPool2d, SumPool2d.

Parameters:

• type (str) –

  Pooling type.

  • A - torch.nn.AvgPool2d.

  • M - torch.nn.MaxPool2d.

  • S - SumPool2d.

• kernel_size (int, optional) – The size of the window. Defaults to 2.

• stride (Optional[int], optional) – The stride of the window. Default value is kernel_size.

Raises:

ValueError – Non-existent pool type.

Methods

get	Initializes and returns the network layer

get(in_channels: int) → Tuple[Module, int]

Initializes and returns the network layer

Parameters:

in_channels (int) – Number of input channels.

Returns:

The generated module and the number of channels that will be after applying this layer to a tensor with in_channels channels.

Return type:

Tuple[nn.Module, int]