mindspore.mint.nn.AdaptiveMaxPool1d

class mindspore.mint.nn.AdaptiveMaxPool1d(output_size, return_indices=False)[source]

Apply a 1-D adaptive max pooling over an input signal composed of several input planes.

The output is of size \(L_{out}\), for any input size. The number of output features is equal to the number of input planes.

Warning

This is an experimental API that is subject to change or deletion.

Note

Atlas training series products do not support backward propagation.

Parameters

output_size (Union[int, tuple]) – The target output size \(L_{out}\).
return_indices (bool, optional) – Whether to return the index of the maximum value. Default: False.

Inputs:

input (Tensor) - The input tensor with shape \((N, C, L_{in})\) or \((C, L_{in})\).

Outputs:

Union(Tensor, tuple(Tensor, Tensor)).

If return_indices is False, output is a Tensor, with shape \((N, C, L_{out})\). It has the same data type as input.
If return_indices is True, output is a Tuple of 2 Tensors, representing the result and where the max values are generated.

Supported Platforms:

Ascend

Examples

>>> import mindspore
>>> input = mindspore.tensor([[[2, 1, 2], [2, 3, 5]]], mindspore.float16)
>>> net = mindspore.mint.nn.AdaptiveMaxPool1d(3)
>>> output = net(input)
>>> print(output)
[[[2. 1. 2.]
  [2. 3. 5.]]]