Spaces:
Running
Running
File size: 3,340 Bytes
e17e8cc |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 |
"""This code is taken from <https://github.com/alexandre01/deepsvg>
by Alexandre Carlier, Martin Danelljan, Alexandre Alahi and Radu Timofte
from the paper >https://arxiv.org/pdf/2007.11301.pdf>
"""
from torch.optim.lr_scheduler import _LRScheduler
from torch.optim.lr_scheduler import ReduceLROnPlateau
class GradualWarmupScheduler(_LRScheduler):
""" Gradually warm-up(increasing) learning rate in optimizer.
Proposed in 'Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour'.
Args:
optimizer (Optimizer): Wrapped optimizer.
multiplier: target learning rate = base lr * multiplier if multiplier > 1.0. if multiplier = 1.0, lr starts from 0 and ends up with the base_lr.
total_epoch: target learning rate is reached at total_epoch, gradually
after_scheduler: after target_epoch, use this scheduler(eg. ReduceLROnPlateau)
"""
def __init__(self, optimizer, multiplier, total_epoch, after_scheduler=None):
self.multiplier = multiplier
if self.multiplier < 1.:
raise ValueError('multiplier should be greater thant or equal to 1.')
self.total_epoch = total_epoch
self.after_scheduler = after_scheduler
self.finished = False
super(GradualWarmupScheduler, self).__init__(optimizer)
def get_lr(self):
if self.last_epoch > self.total_epoch:
if self.after_scheduler:
if not self.finished:
self.after_scheduler.base_lrs = [base_lr * self.multiplier for base_lr in self.base_lrs]
self.finished = True
return self.after_scheduler.get_last_lr()
return [base_lr * self.multiplier for base_lr in self.base_lrs]
if self.multiplier == 1.0:
return [base_lr * (float(self.last_epoch) / self.total_epoch) for base_lr in self.base_lrs]
else:
return [base_lr * ((self.multiplier - 1.) * self.last_epoch / self.total_epoch + 1.) for base_lr in self.base_lrs]
def step_ReduceLROnPlateau(self, metrics, epoch=None):
if epoch is None:
epoch = self.last_epoch + 1
self.last_epoch = epoch if epoch != 0 else 1 # ReduceLROnPlateau is called at the end of epoch, whereas others are called at beginning
if self.last_epoch <= self.total_epoch:
warmup_lr = [base_lr * ((self.multiplier - 1.) * self.last_epoch / self.total_epoch + 1.) for base_lr in self.base_lrs]
for param_group, lr in zip(self.optimizer.param_groups, warmup_lr):
param_group['lr'] = lr
else:
if epoch is None:
self.after_scheduler.step(metrics, None)
else:
self.after_scheduler.step(metrics, epoch - self.total_epoch)
def step(self, epoch=None, metrics=None):
if type(self.after_scheduler) != ReduceLROnPlateau:
if self.finished and self.after_scheduler:
if epoch is None:
self.after_scheduler.step(None)
else:
self.after_scheduler.step(epoch - self.total_epoch)
self._last_lr = self.after_scheduler.get_last_lr()
else:
return super(GradualWarmupScheduler, self).step(epoch)
else:
self.step_ReduceLROnPlateau(metrics, epoch)
|