mindspore.ops.csr_relu

mindspore.ops.csr_relu(x: CSRTensor)

Computes ReLU (Rectified Linear Unit activation function) of input csr_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 (CSRTensor) – Input CSRTensor.

Returns

CSRTensor, with the same dtype and shape as the x.

Raises

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

• TypeError – If x is not a CSRTensor.

Supported Platforms:

Ascend GPU CPU

Examples

>>> indptr = Tensor([0, 1, 2, 2], dtype=mstype.int32)
>>> indices = Tensor([3, 0], dtype=mstype.int32)
>>> values = Tensor([-1, 2], dtype=mstype.float32)
>>> shape = (3, 4)
>>> x = CSRTensor(indptr, indices, values, shape)
>>> output = ops.csr_relu(x)
>>> print(output.values)
[0. 2.]