mindspore.nn.ReLU6

class mindspore.nn.ReLU6[source]

Compute ReLU6 activation function.

ReLU6 is similar to ReLU with a upper limit of 6, which if the inputs are greater than 6, the outputs will be suppressed to 6. It computes element-wise as

\[\min(\max(0, x), 6).\]

The input is a Tensor of any valid shape.

Inputs:
  • x (Tensor) - The input of ReLU6 with data type of float16 or float32. The shape is \((N,*)\) where \(*\) means, any number of additional dimensions.

Outputs:

Tensor, which has the same type as x.

Raises

TypeError – If dtype of x is neither float16 nor float32.

Supported Platforms:

Ascend GPU CPU

Examples

>>> x = Tensor(np.array([-1, -2, 0, 2, 1]), mindspore.float16)
>>> relu6 = nn.ReLU6()
>>> output = relu6(x)
>>> print(output)
[0. 0. 0. 2. 1.]