mindspore.ops.fold

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

Combines an array of sliding local blocks into a large containing tensor.

Consider a batched input tensor of shape $(N,C\times \prod (\text{kernel\_size}),L)$ , where $N$ is the batch dimension, $C\times \prod (\text{kernel\_size})$ 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:

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

where $d$ is over all spatial dimensions.

Therefore, output_size is the spatial shape of the large containing tensor of the sliding local blocks.

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

Warning

• The input must be a 3-dimensional Tensor with shape $(N,C\times \prod (\text{kernel\_size}),L)$ .

• The output must be a 4-dimensional Tensor with shape $(N,C,output\mathrm{\_}size[0],output\mathrm{\_}size[1],...)$ .

Parameters

• input (Tensor) – 3-D Tensor, supported dtypes: float16, float32, float64, complex64 and complex128.

• output_size (Tensor) – 1D tensor with 2 elements of data type int.

• 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 size of the dilation, 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 size of the padding, should be two int for height and width. If type is int, it means that height equal with width. Default: 0 .

• stride (Union[int, tuple[int], list[int]], optional) – The size of the stride, 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 output_size, kernel_size, stride, dilation, padding data type is not int, tuple or list.

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

• ValueError – If padding value is less than zero or elements number more than 2.

• ValueError – If input.shape[1] != kernel_size[0] * kernel_size[1]

• ValueError – If input.shape[2] does not match the calculated number of sliding blocks.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> from mindspore import dtype as mstype
>>> x = Tensor(input_data=np.random.rand(16, 64, 25), dtype=mstype.float32)
>>> output_size = Tensor(input_data=[8, 8], dtype=mstype.int32)
>>> output = ops.fold(x, output_size, [2, 2], [2, 2], [2, 2], [2, 2])
>>> print(output.shape)
(16, 16, 8, 8)