mindspore.mint.nn.PReLU

class mindspore.mint.nn.PReLU(num_parameters=1, init=0.25, dtype=None)[source]

Apply the element-wise PReLU function.

PReLU is defined as:

\[PReLU(x_i)= \max(0, x_i) + w * \min(0, x_i),\]

where \(x_i\) is an element of an channel of the input.

Here \(w\) is a learnable parameter with a default initial value 0.25. Parameter \(w\) has dimensionality of the argument channel. If called without argument channel, a single parameter \(w\) will be shared across all channels.

PReLU Activation Function Graph:

Note

Channel dim is the 2nd dim of input. When input has dims < 2, then there is no channel dim and the number of channels = 1.
In GE mode, the rank of the input tensor must be greater than 1; otherwise, an error will be triggered.

Parameters

num_parameters (int, optional) – number of w to learn. Legitimate values are 1, or the number of channels at tensor input. Default: 1 .
init (float, optional) – the initial value of w. Default: 0.25 .
dtype (mindspore.dtype, optional) – the type of w. Default: None. Supported data type are {float16, float32, bfloat16}.

Inputs:

input (Tensor) - The input tensor.

Outputs:

Tensor.

Supported Platforms:

Ascend

Examples

>>> import mindspore
>>> x = mindspore.tensor([[[[0.1, 0.6], [0.9, 0.9]]]], mindspore.float32)
>>> prelu = mindspore.mint.nn.PReLU()
>>> output = prelu(x)
>>> print(output)
[[[[0.1 0.6]
   [0.9 0.9]]]]