mindspore.ops.relu

mindspore.ops.relu(input)[source]

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

It returns $max (i n p u t, 0)$ element-wise. Specially, the neurons with the negative output will be suppressed and the active neurons will stay the same.

R e L U (i n p u t) = (i n p u t)^{+} = max (0, i n p u t)

Note

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

Parameters

input (Tensor) – Input Tensor of numeric types.

Returns

Tensor, has the same dtype and shape as input_x.

Raises

TypeError – If dtype of input is not a number.
TypeError – If input is not a Tensor.

Supported Platforms:: Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> input_x = Tensor(np.array([[-1.0, 4.0, -8.0], [2.0, -5.0, 9.0]]), mindspore.float32)
>>> output = ops.relu(input_x)
>>> print(output)
[[0. 4. 0.]
 [2. 0. 9.]]