AvgPool2d

class continual.AvgPool2d(kernel_size, stride=None, padding=0, ceil_mode=False, count_include_pad=True, divisor_override=None, dilation=1, temporal_fill='zeros')

Applies a Continual 2D average pooling over an input signal composed of several input planes.

In the simplest case, the output value of the layer with input size $(N, C, T, W)$, output $(N, C, T_{out}, W_{out})$ and kernel_size $(kT, kW)$ can be precisely described as:

$$out(N_i, C_j, h, w) = \frac{1}{kT * kW} \sum_{m=0}^{kT-1} \sum_{n=0}^{kW-1} input(N_i, C_j, stride[0] \times h + m, stride[1] \times w + n)$$

If padding is non-zero, then the input is implicitly zero-padded on both sides for padding number of points.

Note

When stride > 1, the forward_step will only produce non-None values every stride steps.

Note

When ceil_mode=True, sliding windows are allowed to go off-bounds if they start within the left padding or the input. Sliding windows that would start in the right padded region are ignored.

The parameters kernel_size, stride, padding can either be:

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

• a tuple of two ints – in which case, the first int is used for the height dimension, and the second int for the width dimension

Parameters:

• kernel_size (Union[int, Tuple[int, int]]) – the size of the window

• stride (Union[int, Tuple[int, int]]) – the stride of the window. Default value is kernel_size

• padding (Union[int, Tuple[int, int]]) – implicit zero padding to be added on both sides

• ceil_mode (bool) – when True, will use ceil instead of floor to compute the output shape

• count_include_pad (bool) – when True, will include the zero-padding in the averaging calculation

• divisor_override (Optional[int]) – if specified, it will be used as divisor, otherwise size of the pooling region will be used

• dilation (Union[int, Tuple[int, int]]) – The stride between elements within a sliding window, must be > 0. Only temporal dimension is supported

• temporal_fill (PaddingMode) – How temporal states are initialized

Shape:

• Input: $(N, C, T_{in}, W_{in})`$.

• Output: $(N, C, T_{out}, W_{out})`$, where

  $$T_{out} = \left\lfloor\frac{T_{in} + 2 \times \text{padding}[0] - \text{kernel\_size}[0]}{\text{stride}[0]} + 1\right\rfloor$$
  $$W_{out} = \left\lfloor\frac{W_{in} + 2 \times \text{padding}[1] - \text{kernel\_size}[1]}{\text{stride}[1]} + 1\right\rfloor$$

Examples:

m = co.AvgPool2d(3, stride=(2, 1))
x = torch.randn(20, 16, 50, 32)
assert torch.allclose(m.forward(x), m.forward_steps(x), atol=1e-7)