mindspore.ops.unfold

mindspore.ops.unfold(input, kernel_size, dilation=1, padding=0, stride=1)

Extracts sliding local blocks from a batched input tensor.

Consider a batched input tensor of shape $(N,C,\ast )$, where $N$ is the batch dimension, $C$ is the channel dimension, and $\ast$ represent arbitrary spatial dimensions. This operation flattens each sliding Kernel_size- sized block within the spatial dimensions of input x into a column (i.e., last dimension) of a 3-D output tensor of shape $(N,C\times \prod (\text{kernel\_size}),L)$, where $C\times \prod (\text{kernel\_size})$ is the total number of values within each block (a block has $\prod (\text{kernel\_size})$ spatial locations each containing a C-channeled vector), and $L$ is the total number of such blocks:

$$L=\prod _d\lfloor \frac{\text{spatial\_size}[d]+2\times \text{pads}[d]-\text{dilations}[d]\times (\text{kernel\_size}[d]-1)-1}{\text{strides}[d]}+1\rfloor ,$$

where $\text{spatial\_size}$ is formed by the spatial dimensions of input x ($\ast$ above), and $d$ is over all spatial dimensions.

Therefore, indexing output at the last dimension (column dimension) gives all values within a certain block.

The dilation, padding and stride arguments specify how the sliding blocks are retrieved.

Warning

• The output is a 3-dimensional Tensor whose shape is $(N,C\times \prod (\text{kernel\_size}),L)$ .

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

Parameters

• input (Tensor) – 4-D Tensor, supported dtypes: float16, float32, float64, complex64 and complex128.

• kernel_size (Union[int, tuple[int], list[int]]) – The size of the kernel, should be two int for height and width. If type is int, it means that height equal with width. Must be specified.

• dilation (Union[int, tuple[int], list[int]], optional) – The dilation of the window, should be two int for height and width. If type is int, it means that height equal with width. Default: 1 .

• padding (Union[int, tuple[int], list[int]], optional) –

  The pad of the window, that must be a tuple/list of one or two int for height and width. Default: 0 .

  • If one int, pad_height = pad_width.

  • If two int, pad_height = padding[0], pad_width = padding[1].

• stride (Union[int, tuple[int], list[int]], optional) – The stride of the window, should be two int for height and width. If type is int, it means that height equal with width. Default: 1 .

Returns

A Tensor, with same type as input . And its shape is as described above.

Raises

• TypeError – If any data type of kernel_size, stride, dilation, padding is not int, tuple or list.

• ValueError – If kernel_size, dilation, stride value is not greater than zero or elements number more than 2.

• ValueError – If padding value is less than zero.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> x = Tensor(np.random.rand(4, 4, 32, 32), mindspore.float64)
>>> output = ops.unfold(x, kernel_size=3, dilation=1, stride=1)
>>> print(output.shape)
(4, 36, 900)