Why negative grad_input of LF_MMI loss?

jzlianglu / pykaldi2

Yet another speech toolkit based on Kaldi and PyTorch

MIT License

173 stars 33 forks source link

Closed glynpu closed 4 years ago

glynpu commented 4 years ago

Hi,

Why does grad_input multiply -1 in LF_MMI loss Class? grad_input *= -1.0 Code Reference:

Any explanation for this? Thank you

jzlianglu commented 4 years ago

Because we want to maximize the MMI objective, instead of to minimize it.