oneflow.nn.AdaptiveAvgPool2d

class oneflow.nn.AdaptiveAvgPool2d(output_size, data_format=None)

Applies a 2D adaptive average pooling over an input signal composed of several input planes.

The output is of size H x W, for any input size. The number of output features is equal to the number of input planes.

Parameters

output_size – the target output size of the image of the form H x W. Can be a tuple (H, W) or a single H for a square image H x H. H and W can be either a int, or None which means the size will be the same as that of the input.

For example:

>>> import numpy as np
>>> import oneflow as flow
>>> import oneflow.nn as nn

>>> m = nn.AdaptiveAvgPool2d((5,7))
>>> input = flow.Tensor(np.random.randn(1, 64, 8, 9))
>>> output = m(input)
>>> output.size()
oneflow.Size([1, 64, 5, 7])

>>> m = nn.AdaptiveAvgPool2d(7)
>>> input = flow.Tensor(np.random.randn(1, 64, 10, 9))
>>> output = m(input)
>>> output.size()
oneflow.Size([1, 64, 7, 7])

>>> m = nn.AdaptiveAvgPool2d((None, 7))
>>> input = flow.Tensor(np.random.randn(1, 64, 10, 9))
>>> output = m(input)
>>> output.size()
oneflow.Size([1, 64, 10, 7])