LDLMIn construction

class LayerNorm(Module):
    r"""Applies Layer Normalization over a mini-batch of inputs.

    This layer implements the operation as described in
    the paper `Layer Normalization <https://arxiv.org/abs/1607.06450>`__

    .. math::
        y = \frac{x - \mathrm{E}[x]}{ \sqrt{\mathrm{Var}[x] + \epsilon}} * \gamma + \beta

    The mean and standard-deviation are calculated over the last `D` dimensions, where `D`
    is the dimension of :attr:`normalized_shape`. For example, if :attr:`normalized_shape`
    is ``(3, 5)`` (a 2-dimensional shape), the mean and standard-deviation are computed over
    the last 2 dimensions of the input (i.e. ``input.mean((-2, -1))``).
    :math:`\gamma` and :math:`\beta` are learnable affine transform parameters of
    :attr:`normalized_shape` if :attr:`elementwise_affine` is ``True``.
    The standard-deviation is calculated via the biased estimator, equivalent to
    `torch.var(input, unbiased=False)`.

    .. note::
        Unlike Batch Normalization and Instance Normalization, which applies
        scalar scale and bias for each entire channel/plane with the
        :attr:`affine` option, Layer Normalization applies per-element scale and
        bias with :attr:`elementwise_affine`.

    This layer uses statistics computed from input data in both training and
    evaluation modes.

    Args:
        normalized_shape (int or list or torch.Size): input shape from an expected input
            of size

            .. math::
                [* \times \text{normalized\_shape}[0] \times \text{normalized\_shape}[1]
                    \times \ldots \times \text{normalized\_shape}[-1]]

            If a single integer is used, it is treated as a singleton list, and this module will

… lines 126–172 omitted …

    def __init__(self, normalized_shape: _shape_t, eps: float = 1e-5, elementwise_affine: bool = True,
                 bias: bool = True, device=None, dtype=None) -> None:
        factory_kwargs = {'device': device, 'dtype': dtype}
        super().__init__()
        if isinstance(normalized_shape, numbers.Integral):
            # mypy error: incompatible types in assignment
            normalized_shape = (normalized_shape,)  # type: ignore[assignment]
        self.normalized_shape = tuple(normalized_shape)  # type: ignore[arg-type]
        self.eps = eps
        self.elementwise_affine = elementwise_affine
        if self.elementwise_affine:
            self.weight = Parameter(torch.empty(self.normalized_shape, **factory_kwargs))
            if bias:
                self.bias = Parameter(torch.empty(self.normalized_shape, **factory_kwargs))
            else:
                self.register_parameter('bias', None)
        else:
            self.register_parameter('weight', None)
            self.register_parameter('bias', None)

        self.reset_parameters()

    def reset_parameters(self) -> None:
        if self.elementwise_affine:
            init.ones_(self.weight)
            if self.bias is not None:
                init.zeros_(self.bias)

    def forward(self, input: Tensor) -> Tensor:
        return F.layer_norm(
            input, self.normalized_shape, self.weight, self.bias, self.eps)