mindspore.ops.rrelu

mindspore.ops.rrelu(input, lower=1.0 / 8, upper=1.0 / 3)

Randomized Leaky ReLU activation function.

The activation function is defined as:

\[\text{rrelu}(input_{ji}) = \begin{cases}input_{ji}, &\text{if } input_{ji} \geq 0; \cr {\alpha_{ji}} * input_{ji}, &\text{otherwise.}\end{cases}\]

where \(\alpha_{ji}\) ~ \(U(l, u)\), \(l \le u\).

Applies the rrelu function elementally, as described in the paper: Empirical Evaluation of Rectified Activations in Convolution Network .

Parameters

• input (Tensor) – The input of rrelu is a Tensor of any dimension.

• lower (Union[int, float]) – Slope of the activation function at data of input < 0. Default: 1.0 / 8 .

• upper (Union[int, float]) – Slope of the activation function at data of input < 0. Default: 1.0 / 3 .

Returns

Tensor, after rrelu, has the same type and shape as the input.

Raises

• TypeError – If lower is not a float or an int.

• TypeError – If upper is not a float or an int.

• TypeError – If input is not a Tensor.

• TypeError – If input is not a Tensor of mindspore.float16 or mindspore.float32.

• ValueError – If lower is greater than upper.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> x = Tensor(np.array([[-1.0, 4.0], [2.0, 0]]), mindspore.float32)
>>> output = ops.rrelu(x)
>>> print(output)
[[-0.31465699  4.        ]
 [ 2.          0.        ]]