How to use the torchmeta.modules.batchnorm._MetaBatchNorm function in torchmeta

bias = params.get('bias', None)

        return F.batch_norm(
            input, self.running_mean, self.running_var, weight, bias,
            self.training or not self.track_running_stats,
            exponential_average_factor, self.eps)

class MetaBatchNorm1d(_MetaBatchNorm):
    __doc__ = nn.BatchNorm1d.__doc__

    def _check_input_dim(self, input):
        if input.dim() != 2 and input.dim() != 3:
            raise ValueError('expected 2D or 3D input (got {}D input)'
                             .format(input.dim()))

class MetaBatchNorm2d(_MetaBatchNorm):
    __doc__ = nn.BatchNorm2d.__doc__

    def _check_input_dim(self, input):
        if input.dim() != 4:
            raise ValueError('expected 4D input (got {}D input)'
                             .format(input.dim()))

class MetaBatchNorm3d(_MetaBatchNorm):
    __doc__ = nn.BatchNorm3d.__doc__

    def _check_input_dim(self, input):
        if input.dim() != 5:
            raise ValueError('expected 5D input (got {}D input)'
                             .format(input.dim()))

if self.num_batches_tracked is not None:
                self.num_batches_tracked += 1
                if self.momentum is None:  # use cumulative moving average
                    exponential_average_factor = 1.0 / float(self.num_batches_tracked)
                else:  # use exponential moving average
                    exponential_average_factor = self.momentum

        weight = params.get('weight', None)
        bias = params.get('bias', None)

        return F.batch_norm(
            input, self.running_mean, self.running_var, weight, bias,
            self.training or not self.track_running_stats,
            exponential_average_factor, self.eps)

class MetaBatchNorm1d(_MetaBatchNorm):
    __doc__ = nn.BatchNorm1d.__doc__

    def _check_input_dim(self, input):
        if input.dim() != 2 and input.dim() != 3:
            raise ValueError('expected 2D or 3D input (got {}D input)'
                             .format(input.dim()))

class MetaBatchNorm2d(_MetaBatchNorm):
    __doc__ = nn.BatchNorm2d.__doc__

    def _check_input_dim(self, input):
        if input.dim() != 4:
            raise ValueError('expected 4D input (got {}D input)'
                             .format(input.dim()))

class MetaBatchNorm3d(_MetaBatchNorm):

__doc__ = nn.BatchNorm1d.__doc__

    def _check_input_dim(self, input):
        if input.dim() != 2 and input.dim() != 3:
            raise ValueError('expected 2D or 3D input (got {}D input)'
                             .format(input.dim()))

class MetaBatchNorm2d(_MetaBatchNorm):
    __doc__ = nn.BatchNorm2d.__doc__

    def _check_input_dim(self, input):
        if input.dim() != 4:
            raise ValueError('expected 4D input (got {}D input)'
                             .format(input.dim()))

class MetaBatchNorm3d(_MetaBatchNorm):
    __doc__ = nn.BatchNorm3d.__doc__

    def _check_input_dim(self, input):
        if input.dim() != 5:
            raise ValueError('expected 5D input (got {}D input)'
                             .format(input.dim()))