mindspore.ops.ScatterMin

class mindspore.ops.ScatterMin(use_locking=False)[source]

Updates the value of the input tensor through the minimum operation.

Using given values to update tensor value through the min operation, along with the input indices. This operation outputs the input_x after the update is done, which makes it convenient to use the updated value.

for each \(i, ..., j\) in indices.shape:

\[\text{input_x}[\text{indices}[i, ..., j], :] = min(\text{input_x}[\text{indices}[i, ..., j], :], \text{updates}[i, ..., j, :])\]

Inputs of input_x and updates comply with the implicit type conversion rules to make the data types consistent. If they have different data types, the lower priority data type will be converted to the relatively highest priority data type. A RuntimeError will be reported when updates does not support conversion to the data type required by input_x.

Parameters

use_locking (bool) – Whether to protect the assignment by a lock. Default: False.

Inputs:

  • input_x (Parameter) - The target tensor, with data type of Parameter. The shape is \((N,*)\) where \(*\) means,any number of additional dimensions.

  • indices (Tensor) - The index to do min operation whose data type must be mindspore.int32 or mindspore.int64.

  • updates (Tensor) - The tensor doing the min operation with input_x, the data type is same as input_x, the shape is indices.shape + input_x.shape[1:].

Outputs:

Tensor, the updated input_x, has the same shape and type as input_x.

Raises

  • TypeError – If use_locking is not a bool.

  • TypeError – If indices is not an int32 or an int64.

  • ValueError – If the shape of updates is not equal to indices.shape + input_x.shape[1:].

  • RuntimeError – If the data type of input_x and updates conversion of Parameter is required when data type conversion of Parameter is not supported.

  • RuntimeError – On the Ascend platform, the input data dimension of input_x , indices and updates is greater than 8 dimensions.

Supported Platforms:

Ascend GPU CPU

Examples

>>> input_x = Parameter(Tensor(np.array([[0.0, 1.0, 2.0], [0.0, 0.0, 0.0]]), mindspore.float32),
...                     name="input_x")
>>> indices = Tensor(np.array([[0, 0], [1, 1]]), mindspore.int32)
>>> update = Tensor(np.ones([2, 2, 3]), mindspore.float32)
>>> scatter_min = ops.ScatterMin()
>>> output = scatter_min(input_x, indices, update)
>>> print(output)
[[0. 1. 1.]
 [0. 0. 0.]]