AFHMM+SAC: parameter chunk_wise_training is hardcoded

[levaphenyl]

In the AFHMM_SAC class __init__ function, the parameter chunk_wise_training is hardcoded.
Consequence: the AFHMM+SAC will be trained jointly, no matter what the user specified. Handy, when the training data does not fit in RAM :).

This issue is just for referencing, I will open a PR.

[Rithwikksvr]

Yes, if we want to make it support multi chunk training, then we need to compute the average of A, B, Transition matrix over the different chunks

[Rithwikksvr]

Feel feel to submit a pull request. But, @nipunbatra or @MingjunZhong can tell if computing the average values over different chunks is a good idea or not

[levaphenyl]

if we want to make it support multi chunk training, then we need to compute the average of A, B, Transition matrix over the different chunks

Understood. I will adapt the PR with the changes.

[levaphenyl]

Feel feel to submit a pull request. But, @nipunbatra or @MingjunZhong can tell if computing the average values over different chunks is a good idea or not

PR is open. Any review is appreciated.