mindspore.mint.nn.functional.prelu

mindspore.mint.nn.functional.prelu(input, weight)

Parametric Rectified Linear Unit activation function.

PReLU is described in the paper Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. Defined as follows:

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

where \(x_i\) is an element of a channel of the input, w is the weight of the channel.

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.

Parameters

• input (Tensor) – The input Tensor of the activation function.

• weight (Tensor) – Weight Tensor. The size of the weight should be 1 or the number of channels at Tensor input.

Returns

Tensor, with the same shape and dtype as input. For detailed information, please refer to mindspore.mint.nn.PReLU.

Raises

• TypeError – If the input or the weight is not a Tensor.

• ValueError – If the weight is not a 0-D or 1-D Tensor.

Supported Platforms:

Ascend

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, mint
>>> x = Tensor(np.arange(-6, 6).reshape((2, 3, 2)), mindspore.float32)
>>> weight = Tensor(np.array([0.1, 0.6, -0.3]), mindspore.float32)
>>> output = mint.nn.functional.prelu(x, weight)
>>> print(output)
[[[-0.60 -0.50]
  [-2.40 -1.80]
  [ 0.60  0.30]]
 [[ 0.00  1.00]
  [ 2.00  3.00]
  [ 4.0   5.00]]]