chainer.functions.rrelu¶

chainer.functions.rrelu(x, l=1. / 8, u=1. / 3, *, r=None, return_r=False)[source]¶

Randomized Leaky Rectified Liner Unit function.

This function is expressed as

\[f(x)=\max(x, ax),\]

where \(a\) is a random number sampled from a uniform distribution \(U(l, u)\).

See: https://arxiv.org/pdf/1505.00853.pdf

Parameters:	x (`Variable` or `numpy.ndarray` or `cupy.ndarray`) – Input variable. A \((s_1, s_2, ..., s_N)\)-shaped float array. l (float) – The lower bound of the uniform distribution. u (float) – The upper bound of the uniform distribution. r (`numpy.ndarray` or None) – The r to be used for rrelu. The shape and dtype must be the same as `x[0]` and should be on the same device. If `r` is not specified or set to `None`, a `r` will be generated randomly according to the given `l` and `u`. If `r` is specified, `l` and `u` will be ignored. return_r (bool) – If `True`, the r used for rrelu is returned altogether with the output variable. The returned `r` can latter be reused by passing it to `r` argument.
Returns:	When `return_r` is `False` (default), return the output variable. Otherwise returnes the tuple of the output variable and `r` (ndarray). The `r` will be on the same device as the input. A \((s_1, s_2, ..., s_N)\)-shaped float array.
Return type:	Variable or tuple

Example

>>> x = np.array([[-1, 0], [2, -3], [-2, 1]], 'f')
>>> x
array([[-1.,  0.],
       [ 2., -3.],
       [-2.,  1.]], dtype=float32)
>>> F.rrelu(x).data # doctest: +SKIP
array([[-0.24850948,  0.        ],
       [ 2.        , -0.50844127],
       [-0.598535  ,  1.        ]], dtype=float32)