mindspore.Tensor.tile

Tensor.tile(dims) Tensor

Replicates an tensor with given dims times.

Note

On Ascend, the number of dims should not exceed 8, and currently does not support scenarios where more than 4 dimensions are repeated simultaneously.

Parameters

dims (tuple[int]) – The parameter that specifies the number of replications, the parameter type is tuple, and the data type is int, i.e., \((y_1, y_2, ..., y_S)\). Only constant value is allowed.

Returns

Tensor, has the same data type as the self. Suppose the length of dims is d, the dimension of self is self.dim, and the shape of self is \((x_1, x_2, ..., x_S)\).

  • If self.dim = d, then the shape of their corresponding positions can be multiplied, and the shape of Outputs is \((x_1*y_1, x_2*y_2, ..., x_S*y_S)\).

  • If self.dim < d, prepend 1 to the shape of self until their lengths are consistent. Such as set the shape of self as \((1, ..., x_1, x_2, ..., x_S)\), then the shape of their corresponding positions can be multiplied, and the shape of Outputs is \((1*y_1, ..., x_R*y_R, x_S*y_S)\).

  • If self.dim > d, prepend 1 to dims until their lengths are consistent. Such as set the dims as \((1, ..., y_1, y_2, ..., y_S)\), then the shape of their corresponding positions can be multiplied, and the shape of Outputs is \((x_1*1, ..., x_R*y_R, x_S*y_S)\).

Raises
  • TypeError – If dims is not a tuple or not all elements are int.

  • ValueError – If not all elements of dims are greater than or equal to 0.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor
>>> input = Tensor(np.array([[1, 2], [3, 4]]), mindspore.float32)
>>> dims = (2, 3)
>>> output = input.tile(dims)
>>> print(output)
[[1.  2.  1.  2.  1.  2.]
 [3.  4.  3.  4.  3.  4.]
 [1.  2.  1.  2.  1.  2.]
 [3.  4.  3.  4.  3.  4.]]
>>> dims = (2, 3, 2)
>>> output = input.tile(dims)
>>> print(output)
[[[1. 2. 1. 2.]
  [3. 4. 3. 4.]
  [1. 2. 1. 2.]
  [3. 4. 3. 4.]
  [1. 2. 1. 2.]
  [3. 4. 3. 4.]]
 [[1. 2. 1. 2.]
  [3. 4. 3. 4.]
  [1. 2. 1. 2.]
  [3. 4. 3. 4.]
  [1. 2. 1. 2.]
  [3. 4. 3. 4.]]]
Tensor.tile(reps) Tensor

For more details, please refer to mindspore.ops.tile().