init.py 文件源码

def orthogonal(tensor, gain=1):
    """Fills the input Tensor or Variable with a (semi) orthogonal matrix, as
    described in "Exact solutions to the nonlinear dynamics of learning in deep
    linear neural networks" - Saxe, A. et al. (2013). The input tensor must have
    at least 2 dimensions, and for tensors with more than 2 dimensions the
    trailing dimensions are flattened.

    Args:
        tensor: an n-dimensional torch.Tensor or autograd.Variable, where n >= 2
        gain: optional scaling factor

    Examples:
        >>> w = torch.Tensor(3, 5)
        >>> nn.init.orthogonal(w)
    """
    if isinstance(tensor, Variable):
        orthogonal(tensor.data, gain=gain)
        return tensor

    if tensor.ndimension() < 2:
        raise ValueError("Only tensors with 2 or more dimensions are supported")

    rows = tensor.size(0)
    cols = tensor[0].numel()
    flattened = torch.Tensor(rows, cols).normal_(0, 1)

    if rows < cols:
        flattened.t_()

    # Compute the qr factorization
    q, r = torch.qr(flattened)
    # Make Q uniform according to https://arxiv.org/pdf/math-ph/0609050.pdf
    d = torch.diag(r, 0)
    ph = d.sign()
    q *= ph.expand_as(q)

    if rows < cols:
        q.t_()

    tensor.view_as(q).copy_(q)
    tensor.mul_(gain)
    return tensor