about "self.scheduler.step() " and "self.loss.step()"

seathiefwang / MGN-pytorch

Reproduction of paper: Learning Discriminative Features with Multiple Granularities for Person Re-Identification

285 stars 108 forks source link

about "self.scheduler.step() " and "self.loss.step()" #18

Open wanggrun opened 4 years ago

wanggrun commented 4 years ago

https://github.com/seathiefwang/MGN-pytorch/blob/384e82002e40b71157506e23d71e6709fa830757/trainer.py#L34

Hi, thank you for the nice repo!

In the 33rd and 34th line of trainer.py, there are two step functions, i.e., self.scheduler.step() and self.loss.step(). Could you explain the roles of these two functions?