AvgPool1d

class continual.AvgPool1d(kernel_size, stride=None, padding=0, ceil_mode=False, count_include_pad=True, dilation=1, temporal_fill='zeros')

Applies a Continual 1D average pooling over an input signal.

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

$$\text{out}(N_i, C_j, l) = \frac{1}{k} \sum_{m=0}^{k-1} \text{input}(N_i, C_j, \text{stride} \times l + m)$$

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 each be an int or a one-element tuple.

Parameters:

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

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

• padding (Union[int, Tuple[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

• dilation (Union[int, Tuple[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: $(N, C, L_{in})$.

• Output: $(N, C, L_{out})$, where

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

Examples:

m = co.AvgPool1d(3, padding=1)
x = torch.randn(20, 16, 50)
assert torch.allclose(m.forward(x), m.forward_steps(x))