Class SynchronizedBatchNorm1d

lib/nn/modules/batchnorm.py:142–202

r"""Applies Synchronized Batch Normalization over a 2d or 3d input that is seen as a mini-batch. .. math:: y = \frac{x - mean[x]}{ \sqrt{Var[x] + \epsilon}} * gamma + beta This module differs from the built-in PyTorch BatchNorm1d as the mean and standard-deviation are redu

class SynchronizedBatchNorm1d(_SynchronizedBatchNorm):
    r"""Applies Synchronized Batch Normalization over a 2d or 3d input that is seen as a
    mini-batch.

    .. math::

        y = \frac{x - mean[x]}{ \sqrt{Var[x] + \epsilon}} * gamma + beta

    This module differs from the built-in PyTorch BatchNorm1d as the mean and
    standard-deviation are reduced across all devices during training.

    For example, when one uses `nn.DataParallel` to wrap the network during
    training, PyTorch's implementation normalize the tensor on each device using
    the statistics only on that device, which accelerated the computation and
    is also easy to implement, but the statistics might be inaccurate.
    Instead, in this synchronized version, the statistics will be computed
    over all training samples distributed on multiple devices.
    
    Note that, for one-GPU or CPU-only case, this module behaves exactly same
    as the built-in PyTorch implementation.

    The mean and standard-deviation are calculated per-dimension over
    the mini-batches and gamma and beta are learnable parameter vectors
    of size C (where C is the input size).

    During training, this layer keeps a running estimate of its computed mean
    and variance. The running sum is kept with a default momentum of 0.1.

    During evaluation, this running mean/variance is used for normalization.

    Because the BatchNorm is done over the `C` dimension, computing statistics
    on `(N, L)` slices, it's common terminology to call this Temporal BatchNorm

    Args:
        num_features: num_features from an expected input of size
            `batch_size x num_features [x width]`
        eps: a value added to the denominator for numerical stability.
            Default: 1e-5
        momentum: the value used for the running_mean and running_var
            computation. Default: 0.1
        affine: a boolean value that when set to ``True``, gives the layer learnable
            affine parameters. Default: ``True``

    Shape:
        - Input: :math:`(N, C)` or :math:`(N, C, L)`
        - Output: :math:`(N, C)` or :math:`(N, C, L)` (same shape as input)

    Examples:
        >>> # With Learnable Parameters
        >>> m = SynchronizedBatchNorm1d(100)
        >>> # Without Learnable Parameters
        >>> m = SynchronizedBatchNorm1d(100, affine=False)
        >>> input = torch.autograd.Variable(torch.randn(20, 100))
        >>> output = m(input)
    """

    def _check_input_dim(self, input):
        if input.dim() != 2 and input.dim() != 3: