nnsvs.mdn.mdn_get_most_probable_sigma_and_mu

nnsvs.mdn.mdn_get_most_probable_sigma_and_mu(log_pi, log_sigma, mu)[source]

Return the mean and standard deviation of the Gaussian component whose weight coefficient is the largest as the most probable predictions.

Parameters:
  • log_pi (torch.Tensor) – Tensor of shape (B, T, G) or (B, T, G, D_out) The log of multinomial distribution of the Gaussians. B is the batch size, T is data length of this batch, G is num_gaussians of class MDNLayer.

  • log_sigma (torch.Tensor) – Tensor of shape (B, T, G, D_out) The standard deviation of the Gaussians. D_out is out_dim of class MDNLayer.

  • mu (torch.Tensor) – Tensor of shape (B, T, G, D_out) The means of the Gaussians. D_out is out_dim of class MDNLayer.

Returns:

tuple of torch.Tensor

torch.Tensor of shape (B, T, D_out). The standardd deviations of the most probable Gaussian component. torch.Tensor of shape (B, T, D_out). Means of the Gaussians.

Return type:

tuple