mindspore.ops.reshape

mindspore.ops.reshape(input, shape)[source]

Reshape the input tensor based on the given shape.

Note

The -1 in the parameter shape indicates that the size of that dimension is inferred from the other dimensions and the total number of elements in the input tensor.

Parameters

input (Tensor) – The input tensor.
shape (Union[tuple[int], list[int], Tensor[int]]) – New shape.

Returns

Tensor

Supported Platforms:: Ascend GPU CPU

Examples

>>> import mindspore
>>> input = mindspore.tensor([[-0.1, 0.3, 3.6], [0.4, 0.5, -3.2]], mindspore.float32)
>>> # case1: Parameter `shape` does not contain -1.
>>> output = mindspore.ops.reshape(input, (3, 2))
>>> print(output)
[[-0.1  0.3]
 [ 3.6  0.4]
 [ 0.5 -3.2]]
>>> # case2: Parameter `shape` contains -1.
>>> output = mindspore.ops.reshape(input, (-1, 6))
>>> print(output)
[[-0.1  0.3  3.6  0.4  0.5 -3.2]]