About the 'loss.step()' in Trainer.train(), trainer.py

[Vast-Stars]

# in code/trainer.py
def train(self):
        self.scheduler.step()
        self.loss.step()

Is the loss.step() only available for those loss functions that contain parameters update operating such as the loss of GAN?

[yulunzhang]

Hi,
Sorry for my late reply. I'm not quite understand your problem. You can send me emails with more details. Thanks.