A tuple representing resolution for each dimension.
      concat_pos (`bool`, *optional*, defaults to `True`):
        Whether to concatenate the input position encoding to the Fourier features.
      sine_only (`bool`, *optional*, defaults to `False`):
        Whether to use a single phase (sin) or two (sin/cos) for each frequency band.

    Returns:
      `torch.FloatTensor` of shape `(batch_size, sequence_length, n_channels)`: The Fourier position embeddings. If
      `concat_pos` is `True` and `sine_only` is `False`, output dimensions are ordered as: [dim_1, dim_2, ..., dim_d,
      sin(pi*f_1*dim_1), ..., sin(pi*f_K*dim_1), ..., sin(pi*f_1*dim_d), ..., sin(pi*f_K*dim_d), cos(pi*f_1*dim_1),
      ..., cos(pi*f_K*dim_1), ..., cos(pi*f_1*dim_d), ..., cos(pi*f_K*dim_d)], where dim_i is pos[:, i] and f_k is the
      kth frequency band.
    r