mindspore.mint.nn.functional.avg_pool1d

mindspore.mint.nn.functional.avg_pool1d(input, kernel_size, stride=None, padding=0, ceil_mode=False, count_include_pad=True)[source]

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

Typically the input is of shape $(N_{i n}, C_{i n}, L_{i n})$ , avg_pool1d outputs regional average in the $(L_{i n})$ -dimension. Given kernel size as $k s = l_{k e r}$ and stride as $s = s_{0}$ , the operation is as follows.

output (N_{i}, C_{j}, l) = \frac{1}{l_{k e r}} \sum_{n = 0}^{l_{k e r} - 1} input (N_{i}, C_{j}, s_{0} \times l + n)

Warning

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

Parameters

input (Tensor) – Tensor of shape $(N, C_{i n}, L_{i n})$ .
kernel_size (Union(int, tuple[int])) – The size of kernel window used to take the average value.
stride (Union(int, tuple[int]), optional) – The distance of kernel moving. stride can either be an int number or a tuple of one int number. Default: None, the same value as kernel_size.
padding (Union(int, tuple[int]), optional) – The pad length to be filled. padding can either be an integer or a tuple of one integer. Default: 0 .
ceil_mode (bool, optional) – If True, apply ceil instead of floor to compute the output shape. Default: False.
count_include_pad (bool, optional) – If True, include the zero-padding in the averaging calculation. Default: True .

Returns

Tensor of shape $(N, C_{i n}, L_{o u t})$ .

Raises

TypeError – If input is not a Tensor.
TypeError – If kernel_size or stride is not an int.
TypeError – If ceil_mode or count_include_pad is not a bool.
ValueError – If kernel_size or stride is less than 1.
ValueError – If kernel_size or stride or padding is not int nor a tuple whose length is greater than 1.

Supported Platforms:: Ascend

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, mint
>>> input_x = Tensor(np.random.randint(0, 10, [1, 3, 6]), mindspore.float32)
>>> output = mint.nn.functional.avg_pool1d(input_x, kernel_size=6, stride=1)
>>> print(output.shape)
(1, 3, 1)