mindspore.ops.coo_relu

mindspore.ops.coo_relu(x: COOTensor)[source]

Computes ReLU (Rectified Linear Unit activation function) of input coo_tensors element-wise.

It returns \(\max(x,\ 0)\) element-wise. Specially, the neurons with the negative output will be suppressed and the active neurons will stay the same.

\[ReLU(x) = (x)^+ = \max(0, x)\]

Note

In general, this operator is more commonly used. The difference from ReLuV2 is that the ReLuV2 will output one more Mask.

Parameters

x (COOTensor) – Input COOTensor with shape \((N, *)\), where \(*\) means any number of additional dimensions. Its dtype is number.

Returns

COOTensor, has the same shape and dtype as the x.

Raises

TypeError – If dtype of x is not a number.
TypeError – If x is not a COOTensor.

Supported Platforms:: Ascend GPU CPU

Examples

>>> from mindspore import dtype as mstype
>>> from mindspore import Tensor, ops, COOTensor
>>> indices = Tensor([[0, 1], [1, 2]], dtype=mstype.int64)
>>> values = Tensor([-1, 2], dtype=mstype.float32)
>>> shape = (3, 4)
>>> x = COOTensor(indices, values, shape)
>>> output = ops.coo_relu(x)
>>> print(output.values)
[0. 2.]