mindspore.mint.nn.AdaptiveAvgPool1d

View Source On Gitee
class mindspore.mint.nn.AdaptiveAvgPool1d(output_size)[source]

Applies a 1D adaptive average 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.

Parameters

output_size (int) – the target output size \(L_{out}\) .

Inputs:

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

Supported Platforms:

Ascend

Examples

>>> import mindspore
>>> from mindspore import Tensor, mint
>>> import numpy as np
>>> input = Tensor(np.array([[[2, 1, 2], [2, 3, 5]]]), mindspore.float16)
>>> net = mint.nn.AdaptiveAvgPool1d(3)
>>> output = net(input)
>>> print(output)
[[[2. 1. 2.]
  [2. 3. 5.]]]