2899d98932b6accd19d3d46a46cf6c720e9fb5f6,chainer/initializers/orthogonal.py,Orthogonal,__init__,#Orthogonal#Any#Any#Any#,51

Before Change

            raise ValueError(
                "Invalid mode: {}. Choose from {}.".format(
                    repr(mode),
                    ", ".join(repr(m) for m in _orthogonal_constraints)))
        super(Orthogonal, self).__init__(dtype)

    // TODO(Kenta Oono)

After Change

    This initializer first makes a matrix of the same shape as the
    array to be initialized whose elements are drawn independently from
    standard Gaussian distribution.
    Next, it applies QR decomposition to (the transpose of) the matrix.
    To make the decomposition (almost surely) unique, we require the diagonal
    of the triangular matrix R to be non-negative (see e.g. Edelman & Rao,
    https://web.eecs.umich.edu/~rajnrao/Acta05rmt.pdf).
    Then, it initializes the array with the (semi-)orthogonal matrix Q.

Instances