mindspore.nn.Unfold

class mindspore.nn.Unfold(ksizes, strides, rates, padding='valid')[source]

Extracts patches from images. The input tensor must be a 4-D tensor and the data format is NCHW.

Parameters

  • ksizes (Union[tuple[int], list[int]]) – The size of sliding window, must be a tuple or a list of integers, and the format is [1, ksize_row, ksize_col, 1].

  • strides (Union[tuple[int], list[int]]) – Distance between the centers of the two consecutive patches, must be a tuple or list of int, and the format is [1, stride_row, stride_col, 1].

  • rates (Union[tuple[int], list[int]]) – In each extracted patch, the gap between the corresponding dimension pixel positions, must be a tuple or a list of integers, and the format is [1, rate_row, rate_col, 1].

  • padding (str) –

    The type of padding algorithm, is a string whose value is “same” or “valid”, not case sensitive. Default: “valid”.

    • same: Means that the patch can take the part beyond the original image, and this part is filled with 0.

    • valid: Means that the taken patch area must be completely covered in the original image.

Inputs:

  • input_x (Tensor) - A 4-D tensor whose shape is [in_batch, in_depth, in_row, in_col] and data type is number.

Outputs:

Tensor, a 4-D tensor whose data type is same as input_x, and the shape is [out_batch, out_depth, out_row, out_col] where out_batch is the same as the in_batch.

\(out\_depth = ksize\_row * ksize\_col * in\_depth\)

\(out\_row = (in\_row - (ksize\_row + (ksize\_row - 1) * (rate\_row - 1))) // stride\_row + 1\)

\(out\_col = (in\_col - (ksize\_col + (ksize\_col - 1) * (rate\_col - 1))) // stride\_col + 1\)

Raises

  • TypeError – If ksizes, strides or rates is neither a tuple nor list.

  • ValueError – If shape of ksizes, strides or rates is not (1, x_row, x_col, 1).

  • ValueError – If the second and third element of ksizes, strides or rates is less than 1.

Supported Platforms:

Ascend

Examples

>>> net = Unfold(ksizes=[1, 2, 2, 1], strides=[1, 2, 2, 1], rates=[1, 2, 2, 1])
>>> image = Tensor(np.ones([2, 3, 6, 6]), dtype=mstype.float16)
>>> output = net(image)
>>> print(output.shape)
(2, 12, 2, 2)