mindspore.ops.fold

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

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

Warning

  • In version 2.0rc1, the input should be a 4-dimensional Tensor whose shape is \((N, C, H, W)\) .

  • In version 2.0, it must be a 3-dimensional Tensor with shape \((N, C \times H, W)\) .

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 , format of the Tensor is (N, C, H, W).

Raises

  • TypeError – If kernel_size, dilation, padding, stride data type 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 or elements number more than 2.

  • ValueError – If input.shape[2] != kernel_size[0] * kernel_size[1].

  • ValueError – If input.shape[3] does not match the calculated number of sliding blocks.

Supported Platforms:

Ascend GPU CPU

Examples

>>> 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)