mindspore.mint.nn.Unfold

class mindspore.mint.nn.Unfold(kernel_size, dilation=1, padding=0, stride=1)

Extracts sliding local blocks from a batched input tensor into a column matrix.

For details, please refer to mindspore.mint.nn.functional.unfold().

Supported Platforms:

Ascend

Examples

>>> import mindspore
>>> import numpy as np
>>> input = mindspore.tensor(np.random.rand(4, 4, 32, 32), mindspore.float32)
>>> unfold = mindspore.mint.nn.Unfold(kernel_size=3, dilation=1, stride=1)
>>> output = unfold(input)
>>> print(output.shape)
(4, 36, 900)