oneflow.nn.MaxPool1d¶
-
class
oneflow.nn.
MaxPool1d
(kernel_size: Union[int, Tuple[int]], stride: Optional[Union[int, Tuple[int]]] = None, padding: Union[int, Tuple[int]] = 0, dilation: Union[int, Tuple[int]] = 1, return_indices: bool = False, ceil_mode: bool = False)¶ Applies a 1D max pooling over an input signal composed of several input planes.
The interface is consistent with PyTorch. The documentation is referenced from: https://pytorch.org/docs/1.10/generated/torch.nn.MaxPool1d.html.
In the simplest case, the output value of the layer with input size \((N, C, L)\) and output \((N, C, L_{out})\) can be precisely described as:
\[out(N_i, C_j, k) = \max_{m=0, \ldots, \text{kernel\_size} - 1} input(N_i, C_j, stride \times k + m)\]If
padding
is non-zero, then the input is implicitly padded with minimum value on both sides forpadding
number of points.dilation
is the stride between the elements within the sliding window. This link has a nice visualization of the pooling parameters.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.
- Parameters
kernel_size – The size of the sliding window, must be > 0.
stride – The stride of the sliding window, must be > 0. Default value is
kernel_size
.padding – Implicit negative infinity padding to be added on both sides, must be >= 0 and <= kernel_size / 2.
dilation – The stride between elements within a sliding window, must be > 0.
return_indices – If
True
, will return the argmax along with the max values.ceil_mode – If
True
, will use ceil instead of floor to compute the output shape. This ensures that every element in the input tensor is covered by a sliding window.
- Shape:
Input: \((N, C, L_{in})\)
Output: \((N, C, L_{out})\), where
\[L_{out} = \left\lfloor \frac{L_{in} + 2 \times \text{padding} - \text{dilation} \times (\text{kernel_size} - 1) - 1}{\text{stride}} + 1\right\rfloor\]
For example:
import oneflow as flow import numpy as np of_maxpool1d = flow.nn.MaxPool1d(kernel_size=3, padding=1, stride=1) x = flow.Tensor(np.random.randn(1, 4, 4)) y = of_maxpool1d(x) y.shape oneflow.Size([1, 4, 4])