def __call__(self):
learning_rate = lr.PiecewiseDecay(boundaries=self.boundaries,
values=self.values,
last_epoch=self.last_epoch)
if self.warmup_epoch > 0:
learning_rate = lr.LinearWarmup(learning_rate=learning_rate,
warmup_steps=self.warmup_epoch,
start_lr=0.0,
end_lr=self.values[0],
last_epoch=self.last_epoch)
return learning_rate
def __call__(self):
learning_rate = lr.CosineAnnealingDecay(
learning_rate=self.learning_rate,
T_max=self.T_max,
last_epoch=self.last_epoch)
if self.warmup_epoch > 0:
learning_rate = lr.LinearWarmup(learning_rate=learning_rate,
warmup_steps=self.warmup_epoch,
start_lr=0.0,
end_lr=self.learning_rate,
last_epoch=self.last_epoch)
return learning_rate
def __call__(self):
learning_rate = lr.StepDecay(learning_rate=self.learning_rate,
step_size=self.step_size,
gamma=self.gamma,
last_epoch=self.last_epoch)
if self.warmup_epoch > 0:
learning_rate = lr.LinearWarmup(learning_rate=learning_rate,
warmup_steps=self.warmup_epoch,
start_lr=0.0,
end_lr=self.learning_rate,
last_epoch=self.last_epoch)
return learning_rate
def __call__(self):
learning_rate = lr.PolynomialDecay(learning_rate=self.learning_rate,
decay_steps=self.epochs,
end_lr=self.end_lr,
power=self.power,
last_epoch=self.last_epoch)
if self.warmup_epoch > 0:
learning_rate = lr.LinearWarmup(learning_rate=learning_rate,
warmup_steps=self.warmup_epoch,
start_lr=0.0,
end_lr=self.learning_rate,
last_epoch=self.last_epoch)
return learning_rate
def __call__(self):
learning_rate = lr.CosineAnnealingDecay(
learning_rate=self.learning_rate,
T_max=self.T_max,
eta_min=self.eta_min,
last_epoch=self.last_epoch
) if self.T_max > 0 else self.learning_rate
if self.warmup_steps > 0:
learning_rate = lr.LinearWarmup(learning_rate=learning_rate,
warmup_steps=self.warmup_steps,
start_lr=self.warmup_start_lr,
end_lr=self.learning_rate,
last_epoch=self.last_epoch)
return learning_rate