Closed glynpu closed 4 years ago
Hi,
Why does grad_input multiply -1 in LF_MMI loss Class? grad_input *= -1.0 Code Reference:
grad_input *= -1.0
Any explanation for this? Thank you
Because we want to maximize the MMI objective, instead of to minimize it.
Hi,
Why does grad_input multiply -1 in LF_MMI loss Class?
grad_input *= -1.0
Code Reference:Any explanation for this? Thank you