nnmnkwii.autograd.unit_variance_mlpg

nnmnkwii.autograd.unit_variance_mlpg(R, means)[source]

Special case of MLPG assuming data is normalized to have unit variance.

Parameters
  • means (torch.autograd.Variable) – Means, of shape (T x D) or (T*num_windows x static_dim). See nnmnkwii.paramgen.reshape_means() to reshape means from (T x D) to (T*num_windows x static_dim).

  • R (torch.FloatTensor) – MLPG matrix.