prelu.py 文件源码

def prelu(x, W):
    """Parametric ReLU function.

    It accepts two arguments: an input ``x`` and a weight array ``W``
    and computes the output as :math:`PReLU(x) = \\max(x, W*x)`,
    where :math:`*` is an elementwise multiplication for each sample in the
    batch.

    When the PReLU function is combined with two-dimensional convolution, the
    elements of parameter :math:`a` are typically shared across the same filter
    of different pixels. In order to support such usage, this function supports
    the shape of parameter array that indicates leading dimensions of input
    arrays except the batch dimension.

    For example :math:`W` has the shape of :math:`(2, 3, 4)`,
    :math:`x` must have the shape of :math:`(B, 2, 3, 4, S1, ..., SN)`
    where B is batchsize and the number of trailing S's
    is arbitrary non-negative integer.

    Args:
        x (~chainer.Variable): Input variable.
            Its first argument is assumed to be the minibatch dimension.
        W (~chainer.Variable): Weight variable.

    Returns:
        ~chainer.Variable: Output variable

    .. seealso:: :class:`~chainer.links.PReLU`

    """
    return PReLUFunction()(x, W)