mindspore.nn.AdaptiveAvgPool1d

class mindspore.nn.AdaptiveAvgPool1d(output_size)

Applies a 1D adaptive average pooling over an input Tensor which can be regarded as a composition of 1D input planes.

Typically, the input is of shape $(N_{in},C_{in},L_{in})$, AdaptiveAvgPool1d outputs regional average in the $L_{in}$-dimension. The output is of shape $(N_{in},C_{in},L_{out})$, where $L_{out}$ is defined by output_size.

Note

$L_{in}$ must be divisible by output_size.

Parameters

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

Inputs:

• input (Tensor) - Tensor of shape $(N,C_{in},L_{in})$, with float16 or float32 data type.

Outputs:

Tensor of shape $(N,C_{in},L_{out})$, has the same type as input.

Raises

• TypeError – If output_size is not an int.

• TypeError – If input is neither float16 nor float32.

• ValueError – If output_size is less than 1.

• ValueError – If length of shape of input is not equal to 3.

• ValueError – If the last dimension of input is smaller than output_size.

• ValueError – If the last dimension of input is not divisible by output_size.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore as ms
>>> import numpy as np
>>> pool = ms.nn.AdaptiveAvgPool1d(output_size=2)
>>> input = ms.Tensor(np.random.randint(0, 10, [1, 3, 6]), ms.float32)
>>> output = pool(input)
>>> result = output.shape
>>> print(result)
(1, 3, 2)