nnmnkwii.autograd.mlpg¶
-
nnmnkwii.autograd.
mlpg
(means, variances, windows)[source]¶ Maximum Liklihood Paramter Generation (MLPG).
The parameters are almost same as
nnmnkwii.paramgen.mlpg()
expects. The differences are:- The function assumes
means
astorch.autograd.Variable
instead ofnumpy.ndarray
. - The fucntion assumes
variances_frames
astorch.FloatTensor
instead ofnumpy.ndarray
.
Parameters: - means (torch.autograd.Variable) – Means
- variances (torch.FloatTensor) – Variances
- windows (list) – A sequence of window specification
- The function assumes