-
Notifications
You must be signed in to change notification settings - Fork 21.4k
/
lr_scheduler.py
1594 lines (1337 loc) · 67.8 KB
/
lr_scheduler.py
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
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
import types
import math
from torch._six import inf
from functools import wraps
import warnings
import weakref
from collections import Counter
from bisect import bisect_right
from .optimizer import Optimizer
EPOCH_DEPRECATION_WARNING = (
"The epoch parameter in `scheduler.step()` was not necessary and is being "
"deprecated where possible. Please use `scheduler.step()` to step the "
"scheduler. During the deprecation, if epoch is different from None, the "
"closed form is used instead of the new chainable form, where available. "
"Please open an issue if you are unable to replicate your use case: "
"https://github.com/pytorch/pytorch/issues/new/choose."
)
class _LRScheduler(object):
def __init__(self, optimizer, last_epoch=-1, verbose=False):
# Attach optimizer
if not isinstance(optimizer, Optimizer):
raise TypeError('{} is not an Optimizer'.format(
type(optimizer).__name__))
self.optimizer = optimizer
# Initialize epoch and base learning rates
if last_epoch == -1:
for group in optimizer.param_groups:
group.setdefault('initial_lr', group['lr'])
else:
for i, group in enumerate(optimizer.param_groups):
if 'initial_lr' not in group:
raise KeyError("param 'initial_lr' is not specified "
"in param_groups[{}] when resuming an optimizer".format(i))
self.base_lrs = [group['initial_lr'] for group in optimizer.param_groups]
self.last_epoch = last_epoch
# Following https://github.com/pytorch/pytorch/issues/20124
# We would like to ensure that `lr_scheduler.step()` is called after
# `optimizer.step()`
def with_counter(method):
if getattr(method, '_with_counter', False):
# `optimizer.step()` has already been replaced, return.
return method
# Keep a weak reference to the optimizer instance to prevent
# cyclic references.
instance_ref = weakref.ref(method.__self__)
# Get the unbound method for the same purpose.
func = method.__func__
cls = instance_ref().__class__
del method
@wraps(func)
def wrapper(*args, **kwargs):
instance = instance_ref()
instance._step_count += 1
wrapped = func.__get__(instance, cls)
return wrapped(*args, **kwargs)
# Note that the returned function here is no longer a bound method,
# so attributes like `__func__` and `__self__` no longer exist.
wrapper._with_counter = True
return wrapper
self.optimizer.step = with_counter(self.optimizer.step)
self.optimizer._step_count = 0
self._step_count = 0
self.verbose = verbose
self.step()
def state_dict(self):
"""Returns the state of the scheduler as a :class:`dict`.
It contains an entry for every variable in self.__dict__ which
is not the optimizer.
"""
return {key: value for key, value in self.__dict__.items() if key != 'optimizer'}
def load_state_dict(self, state_dict):
"""Loads the schedulers state.
Args:
state_dict (dict): scheduler state. Should be an object returned
from a call to :meth:`state_dict`.
"""
self.__dict__.update(state_dict)
def get_last_lr(self):
""" Return last computed learning rate by current scheduler.
"""
return self._last_lr
def get_lr(self):
# Compute learning rate using chainable form of the scheduler
raise NotImplementedError
def print_lr(self, is_verbose, group, lr, epoch=None):
"""Display the current learning rate.
"""
if is_verbose:
if epoch is None:
print('Adjusting learning rate'
' of group {} to {:.4e}.'.format(group, lr))
else:
print('Epoch {:5d}: adjusting learning rate'
' of group {} to {:.4e}.'.format(epoch, group, lr))
def step(self, epoch=None):
# Raise a warning if old pattern is detected
# https://github.com/pytorch/pytorch/issues/20124
if self._step_count == 1:
if not hasattr(self.optimizer.step, "_with_counter"):
warnings.warn("Seems like `optimizer.step()` has been overridden after learning rate scheduler "
"initialization. Please, make sure to call `optimizer.step()` before "
"`lr_scheduler.step()`. See more details at "
"https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate", UserWarning)
# Just check if there were two first lr_scheduler.step() calls before optimizer.step()
elif self.optimizer._step_count < 1:
warnings.warn("Detected call of `lr_scheduler.step()` before `optimizer.step()`. "
"In PyTorch 1.1.0 and later, you should call them in the opposite order: "
"`optimizer.step()` before `lr_scheduler.step()`. Failure to do this "
"will result in PyTorch skipping the first value of the learning rate schedule. "
"See more details at "
"https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate", UserWarning)
self._step_count += 1
class _enable_get_lr_call:
def __init__(self, o):
self.o = o
def __enter__(self):
self.o._get_lr_called_within_step = True
return self
def __exit__(self, type, value, traceback):
self.o._get_lr_called_within_step = False
with _enable_get_lr_call(self):
if epoch is None:
self.last_epoch += 1
values = self.get_lr()
else:
warnings.warn(EPOCH_DEPRECATION_WARNING, UserWarning)
self.last_epoch = epoch
if hasattr(self, "_get_closed_form_lr"):
values = self._get_closed_form_lr()
else:
values = self.get_lr()
for i, data in enumerate(zip(self.optimizer.param_groups, values)):
param_group, lr = data
param_group['lr'] = lr
self.print_lr(self.verbose, i, lr, epoch)
self._last_lr = [group['lr'] for group in self.optimizer.param_groups]
class LambdaLR(_LRScheduler):
"""Sets the learning rate of each parameter group to the initial lr
times a given function. When last_epoch=-1, sets initial lr as lr.
Args:
optimizer (Optimizer): Wrapped optimizer.
lr_lambda (function or list): A function which computes a multiplicative
factor given an integer parameter epoch, or a list of such
functions, one for each group in optimizer.param_groups.
last_epoch (int): The index of last epoch. Default: -1.
verbose (bool): If ``True``, prints a message to stdout for
each update. Default: ``False``.
Example:
>>> # Assuming optimizer has two groups.
>>> lambda1 = lambda epoch: epoch // 30
>>> lambda2 = lambda epoch: 0.95 ** epoch
>>> scheduler = LambdaLR(optimizer, lr_lambda=[lambda1, lambda2])
>>> for epoch in range(100):
>>> train(...)
>>> validate(...)
>>> scheduler.step()
"""
def __init__(self, optimizer, lr_lambda, last_epoch=-1, verbose=False):
self.optimizer = optimizer
if not isinstance(lr_lambda, list) and not isinstance(lr_lambda, tuple):
self.lr_lambdas = [lr_lambda] * len(optimizer.param_groups)
else:
if len(lr_lambda) != len(optimizer.param_groups):
raise ValueError("Expected {} lr_lambdas, but got {}".format(
len(optimizer.param_groups), len(lr_lambda)))
self.lr_lambdas = list(lr_lambda)
super(LambdaLR, self).__init__(optimizer, last_epoch, verbose)
def state_dict(self):
"""Returns the state of the scheduler as a :class:`dict`.
It contains an entry for every variable in self.__dict__ which
is not the optimizer.
The learning rate lambda functions will only be saved if they are callable objects
and not if they are functions or lambdas.
When saving or loading the scheduler, please make sure to also save or load the state of the optimizer.
"""
state_dict = {key: value for key, value in self.__dict__.items() if key not in ('optimizer', 'lr_lambdas')}
state_dict['lr_lambdas'] = [None] * len(self.lr_lambdas)
for idx, fn in enumerate(self.lr_lambdas):
if not isinstance(fn, types.FunctionType):
state_dict['lr_lambdas'][idx] = fn.__dict__.copy()
return state_dict
def load_state_dict(self, state_dict):
"""Loads the schedulers state.
When saving or loading the scheduler, please make sure to also save or load the state of the optimizer.
Args:
state_dict (dict): scheduler state. Should be an object returned
from a call to :meth:`state_dict`.
"""
lr_lambdas = state_dict.pop('lr_lambdas')
self.__dict__.update(state_dict)
# Restore state_dict keys in order to prevent side effects
# https://github.com/pytorch/pytorch/issues/32756
state_dict['lr_lambdas'] = lr_lambdas
for idx, fn in enumerate(lr_lambdas):
if fn is not None:
self.lr_lambdas[idx].__dict__.update(fn)
def get_lr(self):
if not self._get_lr_called_within_step:
warnings.warn("To get the last learning rate computed by the scheduler, "
"please use `get_last_lr()`.")
return [base_lr * lmbda(self.last_epoch)
for lmbda, base_lr in zip(self.lr_lambdas, self.base_lrs)]
class MultiplicativeLR(_LRScheduler):
"""Multiply the learning rate of each parameter group by the factor given
in the specified function. When last_epoch=-1, sets initial lr as lr.
Args:
optimizer (Optimizer): Wrapped optimizer.
lr_lambda (function or list): A function which computes a multiplicative
factor given an integer parameter epoch, or a list of such
functions, one for each group in optimizer.param_groups.
last_epoch (int): The index of last epoch. Default: -1.
verbose (bool): If ``True``, prints a message to stdout for
each update. Default: ``False``.
Example:
>>> lmbda = lambda epoch: 0.95
>>> scheduler = MultiplicativeLR(optimizer, lr_lambda=lmbda)
>>> for epoch in range(100):
>>> train(...)
>>> validate(...)
>>> scheduler.step()
"""
def __init__(self, optimizer, lr_lambda, last_epoch=-1, verbose=False):
self.optimizer = optimizer
if not isinstance(lr_lambda, list) and not isinstance(lr_lambda, tuple):
self.lr_lambdas = [lr_lambda] * len(optimizer.param_groups)
else:
if len(lr_lambda) != len(optimizer.param_groups):
raise ValueError("Expected {} lr_lambdas, but got {}".format(
len(optimizer.param_groups), len(lr_lambda)))
self.lr_lambdas = list(lr_lambda)
super(MultiplicativeLR, self).__init__(optimizer, last_epoch, verbose)
def state_dict(self):
"""Returns the state of the scheduler as a :class:`dict`.
It contains an entry for every variable in self.__dict__ which
is not the optimizer.
The learning rate lambda functions will only be saved if they are callable objects
and not if they are functions or lambdas.
"""
state_dict = {key: value for key, value in self.__dict__.items() if key not in ('optimizer', 'lr_lambdas')}
state_dict['lr_lambdas'] = [None] * len(self.lr_lambdas)
for idx, fn in enumerate(self.lr_lambdas):
if not isinstance(fn, types.FunctionType):
state_dict['lr_lambdas'][idx] = fn.__dict__.copy()
return state_dict
def load_state_dict(self, state_dict):
"""Loads the schedulers state.
Args:
state_dict (dict): scheduler state. Should be an object returned
from a call to :meth:`state_dict`.
"""
lr_lambdas = state_dict.pop('lr_lambdas')
self.__dict__.update(state_dict)
# Restore state_dict keys in order to prevent side effects
# https://github.com/pytorch/pytorch/issues/32756
state_dict['lr_lambdas'] = lr_lambdas
for idx, fn in enumerate(lr_lambdas):
if fn is not None:
self.lr_lambdas[idx].__dict__.update(fn)
def get_lr(self):
if not self._get_lr_called_within_step:
warnings.warn("To get the last learning rate computed by the scheduler, "
"please use `get_last_lr()`.", UserWarning)
if self.last_epoch > 0:
return [group['lr'] * lmbda(self.last_epoch)
for lmbda, group in zip(self.lr_lambdas, self.optimizer.param_groups)]
else:
return [group['lr'] for group in self.optimizer.param_groups]
class StepLR(_LRScheduler):
"""Decays the learning rate of each parameter group by gamma every
step_size epochs. Notice that such decay can happen simultaneously with
other changes to the learning rate from outside this scheduler. When
last_epoch=-1, sets initial lr as lr.
Args:
optimizer (Optimizer): Wrapped optimizer.
step_size (int): Period of learning rate decay.
gamma (float): Multiplicative factor of learning rate decay.
Default: 0.1.
last_epoch (int): The index of last epoch. Default: -1.
verbose (bool): If ``True``, prints a message to stdout for
each update. Default: ``False``.
Example:
>>> # Assuming optimizer uses lr = 0.05 for all groups
>>> # lr = 0.05 if epoch < 30
>>> # lr = 0.005 if 30 <= epoch < 60
>>> # lr = 0.0005 if 60 <= epoch < 90
>>> # ...
>>> scheduler = StepLR(optimizer, step_size=30, gamma=0.1)
>>> for epoch in range(100):
>>> train(...)
>>> validate(...)
>>> scheduler.step()
"""
def __init__(self, optimizer, step_size, gamma=0.1, last_epoch=-1, verbose=False):
self.step_size = step_size
self.gamma = gamma
super(StepLR, self).__init__(optimizer, last_epoch, verbose)
def get_lr(self):
if not self._get_lr_called_within_step:
warnings.warn("To get the last learning rate computed by the scheduler, "
"please use `get_last_lr()`.", UserWarning)
if (self.last_epoch == 0) or (self.last_epoch % self.step_size != 0):
return [group['lr'] for group in self.optimizer.param_groups]
return [group['lr'] * self.gamma
for group in self.optimizer.param_groups]
def _get_closed_form_lr(self):
return [base_lr * self.gamma ** (self.last_epoch // self.step_size)
for base_lr in self.base_lrs]
class MultiStepLR(_LRScheduler):
"""Decays the learning rate of each parameter group by gamma once the
number of epoch reaches one of the milestones. Notice that such decay can
happen simultaneously with other changes to the learning rate from outside
this scheduler. When last_epoch=-1, sets initial lr as lr.
Args:
optimizer (Optimizer): Wrapped optimizer.
milestones (list): List of epoch indices. Must be increasing.
gamma (float): Multiplicative factor of learning rate decay.
Default: 0.1.
last_epoch (int): The index of last epoch. Default: -1.
verbose (bool): If ``True``, prints a message to stdout for
each update. Default: ``False``.
Example:
>>> # Assuming optimizer uses lr = 0.05 for all groups
>>> # lr = 0.05 if epoch < 30
>>> # lr = 0.005 if 30 <= epoch < 80
>>> # lr = 0.0005 if epoch >= 80
>>> scheduler = MultiStepLR(optimizer, milestones=[30,80], gamma=0.1)
>>> for epoch in range(100):
>>> train(...)
>>> validate(...)
>>> scheduler.step()
"""
def __init__(self, optimizer, milestones, gamma=0.1, last_epoch=-1, verbose=False):
self.milestones = Counter(milestones)
self.gamma = gamma
super(MultiStepLR, self).__init__(optimizer, last_epoch, verbose)
def get_lr(self):
if not self._get_lr_called_within_step:
warnings.warn("To get the last learning rate computed by the scheduler, "
"please use `get_last_lr()`.", UserWarning)
if self.last_epoch not in self.milestones:
return [group['lr'] for group in self.optimizer.param_groups]
return [group['lr'] * self.gamma ** self.milestones[self.last_epoch]
for group in self.optimizer.param_groups]
def _get_closed_form_lr(self):
milestones = list(sorted(self.milestones.elements()))
return [base_lr * self.gamma ** bisect_right(milestones, self.last_epoch)
for base_lr in self.base_lrs]
class ConstantLR(_LRScheduler):
"""Decays the learning rate of each parameter group by a small constant factor until the
number of epoch reaches a pre-defined milestone: total_iters. Notice that such decay can
happen simultaneously with other changes to the learning rate from outside this scheduler.
When last_epoch=-1, sets initial lr as lr.
Args:
optimizer (Optimizer): Wrapped optimizer.
factor (float): The number we multiply learning rate until the milestone. Default: 1./3.
total_iters (int): The number of steps that the scheduler decays the learning rate.
Default: 5.
last_epoch (int): The index of the last epoch. Default: -1.
verbose (bool): If ``True``, prints a message to stdout for
each update. Default: ``False``.
Example:
>>> # Assuming optimizer uses lr = 0.05 for all groups
>>> # lr = 0.025 if epoch == 0
>>> # lr = 0.025 if epoch == 1
>>> # lr = 0.025 if epoch == 2
>>> # lr = 0.025 if epoch == 3
>>> # lr = 0.05 if epoch >= 4
>>> scheduler = ConstantLR(self.opt, factor=0.5, total_iters=4)
>>> for epoch in range(100):
>>> train(...)
>>> validate(...)
>>> scheduler.step()
"""
def __init__(self, optimizer, factor=1.0 / 3, total_iters=5, last_epoch=-1, verbose=False):
if factor > 1.0 or factor < 0:
raise ValueError('Constant multiplicative factor expected to be between 0 and 1.')
self.factor = factor
self.total_iters = total_iters
super(ConstantLR, self).__init__(optimizer, last_epoch, verbose)
def get_lr(self):
if not self._get_lr_called_within_step:
warnings.warn("To get the last learning rate computed by the scheduler, "
"please use `get_last_lr()`.", UserWarning)
if self.last_epoch == 0:
return [group['lr'] * self.factor for group in self.optimizer.param_groups]
if (self.last_epoch > self.total_iters or
(self.last_epoch != self.total_iters)):
return [group['lr'] for group in self.optimizer.param_groups]
if (self.last_epoch == self.total_iters):
return [group['lr'] * (1.0 / self.factor) for group in self.optimizer.param_groups]
def _get_closed_form_lr(self):
return [base_lr * (self.factor + (self.last_epoch >= self.total_iters) * (1 - self.factor))
for base_lr in self.base_lrs]
class LinearLR(_LRScheduler):
"""Decays the learning rate of each parameter group by linearly changing small
multiplicative factor until the number of epoch reaches a pre-defined milestone: total_iters.
Notice that such decay can happen simultaneously with other changes to the learning rate
from outside this scheduler. When last_epoch=-1, sets initial lr as lr.
Args:
optimizer (Optimizer): Wrapped optimizer.
start_factor (float): The number we multiply learning rate in the first epoch.
The multiplication factor changes towards end_factor in the following epochs.
Default: 1./3.
end_factor (float): The number we multiply learning rate at the end of linear changing
process. Default: 1.0.
total_iters (int): The number of iterations that multiplicative factor reaches to 1.
Default: 5.
last_epoch (int): The index of the last epoch. Default: -1.
verbose (bool): If ``True``, prints a message to stdout for
each update. Default: ``False``.
Example:
>>> # Assuming optimizer uses lr = 0.05 for all groups
>>> # lr = 0.025 if epoch == 0
>>> # lr = 0.03125 if epoch == 1
>>> # lr = 0.0375 if epoch == 2
>>> # lr = 0.04375 if epoch == 3
>>> # lr = 0.05 if epoch >= 4
>>> scheduler = LinearLR(self.opt, start_factor=0.5, total_iters=4)
>>> for epoch in range(100):
>>> train(...)
>>> validate(...)
>>> scheduler.step()
"""
def __init__(self, optimizer, start_factor=1.0 / 3, end_factor=1.0, total_iters=5, last_epoch=-1,
verbose=False):
if start_factor > 1.0 or start_factor < 0:
raise ValueError('Starting multiplicative factor expected to be between 0 and 1.')
if end_factor > 1.0 or end_factor < 0:
raise ValueError('Ending multiplicative factor expected to be between 0 and 1.')
self.start_factor = start_factor
self.end_factor = end_factor
self.total_iters = total_iters
super(LinearLR, self).__init__(optimizer, last_epoch, verbose)
def get_lr(self):
if not self._get_lr_called_within_step:
warnings.warn("To get the last learning rate computed by the scheduler, "
"please use `get_last_lr()`.", UserWarning)
if self.last_epoch == 0:
return [group['lr'] * self.start_factor for group in self.optimizer.param_groups]
if (self.last_epoch > self.total_iters):
return [group['lr'] for group in self.optimizer.param_groups]
return [group['lr'] * (1. + (self.end_factor - self.start_factor) /
(self.total_iters * self.start_factor + (self.last_epoch - 1) * (self.end_factor - self.start_factor)))
for group in self.optimizer.param_groups]
def _get_closed_form_lr(self):
return [base_lr * (self.start_factor +
(self.end_factor - self.start_factor) * min(self.total_iters, self.last_epoch) / self.total_iters)
for base_lr in self.base_lrs]
class ExponentialLR(_LRScheduler):
"""Decays the learning rate of each parameter group by gamma every epoch.
When last_epoch=-1, sets initial lr as lr.
Args:
optimizer (Optimizer): Wrapped optimizer.
gamma (float): Multiplicative factor of learning rate decay.
last_epoch (int): The index of last epoch. Default: -1.
verbose (bool): If ``True``, prints a message to stdout for
each update. Default: ``False``.
"""
def __init__(self, optimizer, gamma, last_epoch=-1, verbose=False):
self.gamma = gamma
super(ExponentialLR, self).__init__(optimizer, last_epoch, verbose)
def get_lr(self):
if not self._get_lr_called_within_step:
warnings.warn("To get the last learning rate computed by the scheduler, "
"please use `get_last_lr()`.", UserWarning)
if self.last_epoch == 0:
return [group['lr'] for group in self.optimizer.param_groups]
return [group['lr'] * self.gamma
for group in self.optimizer.param_groups]
def _get_closed_form_lr(self):
return [base_lr * self.gamma ** self.last_epoch
for base_lr in self.base_lrs]
class SequentialLR(_LRScheduler):
"""Receives the list of schedulers that is expected to be called sequentially during
optimization process and milestone points that provides exact intervals to reflect
which scheduler is supposed to be called at a given epoch.
Args:
schedulers (list): List of chained schedulers.
milestones (list): List of integers that reflects milestone points.
Example:
>>> # Assuming optimizer uses lr = 1. for all groups
>>> # lr = 0.1 if epoch == 0
>>> # lr = 0.1 if epoch == 1
>>> # lr = 0.9 if epoch == 2
>>> # lr = 0.81 if epoch == 3
>>> # lr = 0.729 if epoch == 4
>>> scheduler1 = ConstantLR(self.opt, factor=0.1, total_iters=2)
>>> scheduler2 = ExponentialLR(self.opt, gamma=0.9)
>>> scheduler = SequentialLR(self.opt, schedulers=[scheduler1, scheduler2], milestones=[2])
>>> for epoch in range(100):
>>> train(...)
>>> validate(...)
>>> scheduler.step()
"""
def __init__(self, optimizer, schedulers, milestones, last_epoch=-1, verbose=False):
for scheduler_idx in range(1, len(schedulers)):
if (schedulers[scheduler_idx].optimizer != schedulers[0].optimizer):
raise ValueError(
"Sequential Schedulers expects all schedulers to belong to the same optimizer, but "
"got schedulers at index {} and {} to be different".format(0, scheduler_idx)
)
if (len(milestones) != len(schedulers) - 1):
raise ValueError(
"Sequential Schedulers expects number of schedulers provided to be one more "
"than the number of milestone points, but got number of schedulers {} and the "
"number of milestones to be equal to {}".format(len(schedulers), len(milestones))
)
self._schedulers = schedulers
self._milestones = milestones
self.last_epoch = last_epoch + 1
self.optimizer = optimizer
def step(self):
self.last_epoch += 1
idx = bisect_right(self._milestones, self.last_epoch)
if idx > 0 and self._milestones[idx - 1] == self.last_epoch:
self._schedulers[idx].step(0)
else:
self._schedulers[idx].step()
def state_dict(self):
"""Returns the state of the scheduler as a :class:`dict`.
It contains an entry for every variable in self.__dict__ which
is not the optimizer.
The wrapped scheduler states will also be saved.
"""
state_dict = {key: value for key, value in self.__dict__.items() if key not in ('optimizer', '_schedulers')}
state_dict['_schedulers'] = [None] * len(self._schedulers)
for idx, s in enumerate(self._schedulers):
state_dict['_schedulers'][idx] = s.state_dict()
return state_dict
def load_state_dict(self, state_dict):
"""Loads the schedulers state.
Args:
state_dict (dict): scheduler state. Should be an object returned
from a call to :meth:`state_dict`.
"""
_schedulers = state_dict.pop('_schedulers')
self.__dict__.update(state_dict)
# Restore state_dict keys in order to prevent side effects
# https://github.com/pytorch/pytorch/issues/32756
state_dict['_schedulers'] = _schedulers
for idx, s in enumerate(_schedulers):
self._schedulers[idx].load_state_dict(s)
class CosineAnnealingLR(_LRScheduler):
r"""Set the learning rate of each parameter group using a cosine annealing
schedule, where :math:`\eta_{max}` is set to the initial lr and
:math:`T_{cur}` is the number of epochs since the last restart in SGDR:
.. math::
\begin{aligned}
\eta_t & = \eta_{min} + \frac{1}{2}(\eta_{max} - \eta_{min})\left(1
+ \cos\left(\frac{T_{cur}}{T_{max}}\pi\right)\right),
& T_{cur} \neq (2k+1)T_{max}; \\
\eta_{t+1} & = \eta_{t} + \frac{1}{2}(\eta_{max} - \eta_{min})
\left(1 - \cos\left(\frac{1}{T_{max}}\pi\right)\right),
& T_{cur} = (2k+1)T_{max}.
\end{aligned}
When last_epoch=-1, sets initial lr as lr. Notice that because the schedule
is defined recursively, the learning rate can be simultaneously modified
outside this scheduler by other operators. If the learning rate is set
solely by this scheduler, the learning rate at each step becomes:
.. math::
\eta_t = \eta_{min} + \frac{1}{2}(\eta_{max} - \eta_{min})\left(1 +
\cos\left(\frac{T_{cur}}{T_{max}}\pi\right)\right)
It has been proposed in
`SGDR: Stochastic Gradient Descent with Warm Restarts`_. Note that this only
implements the cosine annealing part of SGDR, and not the restarts.
Args:
optimizer (Optimizer): Wrapped optimizer.
T_max (int): Maximum number of iterations.
eta_min (float): Minimum learning rate. Default: 0.
last_epoch (int): The index of last epoch. Default: -1.
verbose (bool): If ``True``, prints a message to stdout for
each update. Default: ``False``.
.. _SGDR\: Stochastic Gradient Descent with Warm Restarts:
https://arxiv.org/abs/1608.03983
"""
def __init__(self, optimizer, T_max, eta_min=0, last_epoch=-1, verbose=False):
self.T_max = T_max
self.eta_min = eta_min
super(CosineAnnealingLR, self).__init__(optimizer, last_epoch, verbose)
def get_lr(self):
if not self._get_lr_called_within_step:
warnings.warn("To get the last learning rate computed by the scheduler, "
"please use `get_last_lr()`.", UserWarning)
if self.last_epoch == 0:
return [group['lr'] for group in self.optimizer.param_groups]
elif (self.last_epoch - 1 - self.T_max) % (2 * self.T_max) == 0:
return [group['lr'] + (base_lr - self.eta_min) *
(1 - math.cos(math.pi / self.T_max)) / 2
for base_lr, group in
zip(self.base_lrs, self.optimizer.param_groups)]
return [(1 + math.cos(math.pi * self.last_epoch / self.T_max)) /
(1 + math.cos(math.pi * (self.last_epoch - 1) / self.T_max)) *
(group['lr'] - self.eta_min) + self.eta_min
for group in self.optimizer.param_groups]
def _get_closed_form_lr(self):
return [self.eta_min + (base_lr - self.eta_min) *
(1 + math.cos(math.pi * self.last_epoch / self.T_max)) / 2
for base_lr in self.base_lrs]
class ChainedScheduler(_LRScheduler):
"""Chains list of learning rate schedulers. It takes a list of chainable learning
rate schedulers and performs consecutive step() functions belong to them by just
one call.
Args:
schedulers (list): List of chained schedulers.
Example:
>>> # Assuming optimizer uses lr = 1. for all groups
>>> # lr = 0.09 if epoch == 0
>>> # lr = 0.081 if epoch == 1
>>> # lr = 0.729 if epoch == 2
>>> # lr = 0.6561 if epoch == 3
>>> # lr = 0.59049 if epoch >= 4
>>> scheduler1 = ConstantLR(self.opt, factor=0.1, total_iters=2)
>>> scheduler2 = ExponentialLR(self.opt, gamma=0.9)
>>> scheduler = ChainedScheduler([scheduler1, scheduler2])
>>> for epoch in range(100):
>>> train(...)
>>> validate(...)
>>> scheduler.step()
"""
def __init__(self, schedulers):
for scheduler_idx in range(1, len(schedulers)):
if (schedulers[scheduler_idx].optimizer != schedulers[0].optimizer):
raise ValueError(
"ChainedScheduler expects all schedulers to belong to the same optimizer, but "
"got schedulers at index {} and {} to be different".format(0, scheduler_idx)
)
self._schedulers = list(schedulers)
self.optimizer = schedulers[0].optimizer
def step(self):
for scheduler in self._schedulers:
scheduler.step()
def state_dict(self):
"""Returns the state of the scheduler as a :class:`dict`.
It contains an entry for every variable in self.__dict__ which
is not the optimizer.
The wrapped scheduler states will also be saved.
"""
state_dict = {key: value for key, value in self.__dict__.items() if key not in ('optimizer', '_schedulers')}
state_dict['_schedulers'] = [None] * len(self._schedulers)
for idx, s in enumerate(self._schedulers):
state_dict['_schedulers'][idx] = s.state_dict()
return state_dict
def load_state_dict(self, state_dict):
"""Loads the schedulers state.
Args:
state_dict (dict): scheduler state. Should be an object returned
from a call to :meth:`state_dict`.
"""
_schedulers = state_dict.pop('_schedulers')
self.__dict__.update(state_dict)
# Restore state_dict keys in order to prevent side effects
# https://github.com/pytorch/pytorch/issues/32756
state_dict['_schedulers'] = _schedulers
for idx, s in enumerate(_schedulers):
self._schedulers[idx].load_state_dict(s)
class ReduceLROnPlateau(object):
"""Reduce learning rate when a metric has stopped improving.
Models often benefit from reducing the learning rate by a factor
of 2-10 once learning stagnates. This scheduler reads a metrics
quantity and if no improvement is seen for a 'patience' number
of epochs, the learning rate is reduced.
Args:
optimizer (Optimizer): Wrapped optimizer.
mode (str): One of `min`, `max`. In `min` mode, lr will
be reduced when the quantity monitored has stopped
decreasing; in `max` mode it will be reduced when the
quantity monitored has stopped increasing. Default: 'min'.
factor (float): Factor by which the learning rate will be
reduced. new_lr = lr * factor. Default: 0.1.
patience (int): Number of epochs with no improvement after
which learning rate will be reduced. For example, if
`patience = 2`, then we will ignore the first 2 epochs
with no improvement, and will only decrease the LR after the
3rd epoch if the loss still hasn't improved then.
Default: 10.
threshold (float): Threshold for measuring the new optimum,
to only focus on significant changes. Default: 1e-4.
threshold_mode (str): One of `rel`, `abs`. In `rel` mode,
dynamic_threshold = best * ( 1 + threshold ) in 'max'
mode or best * ( 1 - threshold ) in `min` mode.
In `abs` mode, dynamic_threshold = best + threshold in
`max` mode or best - threshold in `min` mode. Default: 'rel'.
cooldown (int): Number of epochs to wait before resuming
normal operation after lr has been reduced. Default: 0.
min_lr (float or list): A scalar or a list of scalars. A
lower bound on the learning rate of all param groups
or each group respectively. Default: 0.
eps (float): Minimal decay applied to lr. If the difference
between new and old lr is smaller than eps, the update is
ignored. Default: 1e-8.
verbose (bool): If ``True``, prints a message to stdout for
each update. Default: ``False``.
Example:
>>> optimizer = torch.optim.SGD(model.parameters(), lr=0.1, momentum=0.9)
>>> scheduler = ReduceLROnPlateau(optimizer, 'min')
>>> for epoch in range(10):
>>> train(...)
>>> val_loss = validate(...)
>>> # Note that step should be called after validate()
>>> scheduler.step(val_loss)
"""
def __init__(self, optimizer, mode='min', factor=0.1, patience=10,
threshold=1e-4, threshold_mode='rel', cooldown=0,
min_lr=0, eps=1e-8, verbose=False):
if factor >= 1.0:
raise ValueError('Factor should be < 1.0.')
self.factor = factor
# Attach optimizer
if not isinstance(optimizer, Optimizer):
raise TypeError('{} is not an Optimizer'.format(
type(optimizer).__name__))
self.optimizer = optimizer
if isinstance(min_lr, list) or isinstance(min_lr, tuple):
if len(min_lr) != len(optimizer.param_groups):
raise ValueError("expected {} min_lrs, got {}".format(
len(optimizer.param_groups), len(min_lr)))
self.min_lrs = list(min_lr)
else:
self.min_lrs = [min_lr] * len(optimizer.param_groups)
self.patience = patience
self.verbose = verbose
self.cooldown = cooldown
self.cooldown_counter = 0
self.mode = mode
self.threshold = threshold
self.threshold_mode = threshold_mode
self.best = None
self.num_bad_epochs = None
self.mode_worse = None # the worse value for the chosen mode
self.eps = eps
self.last_epoch = 0
self._init_is_better(mode=mode, threshold=threshold,
threshold_mode=threshold_mode)
self._reset()
def _reset(self):
"""Resets num_bad_epochs counter and cooldown counter."""
self.best = self.mode_worse
self.cooldown_counter = 0
self.num_bad_epochs = 0
def step(self, metrics, epoch=None):
# convert `metrics` to float, in case it's a zero-dim Tensor
current = float(metrics)
if epoch is None:
epoch = self.last_epoch + 1
else:
warnings.warn(EPOCH_DEPRECATION_WARNING, UserWarning)
self.last_epoch = epoch
if self.is_better(current, self.best):
self.best = current
self.num_bad_epochs = 0
else:
self.num_bad_epochs += 1
if self.in_cooldown:
self.cooldown_counter -= 1
self.num_bad_epochs = 0 # ignore any bad epochs in cooldown
if self.num_bad_epochs > self.patience:
self._reduce_lr(epoch)
self.cooldown_counter = self.cooldown
self.num_bad_epochs = 0
self._last_lr = [group['lr'] for group in self.optimizer.param_groups]
def _reduce_lr(self, epoch):
for i, param_group in enumerate(self.optimizer.param_groups):
old_lr = float(param_group['lr'])
new_lr = max(old_lr * self.factor, self.min_lrs[i])
if old_lr - new_lr > self.eps:
param_group['lr'] = new_lr
if self.verbose:
print('Epoch {:5d}: reducing learning rate'
' of group {} to {:.4e}.'.format(epoch, i, new_lr))
@property
def in_cooldown(self):
return self.cooldown_counter > 0
def is_better(self, a, best):
if self.mode == 'min' and self.threshold_mode == 'rel':
rel_epsilon = 1. - self.threshold
return a < best * rel_epsilon
elif self.mode == 'min' and self.threshold_mode == 'abs':
return a < best - self.threshold
elif self.mode == 'max' and self.threshold_mode == 'rel':
rel_epsilon = self.threshold + 1.
return a > best * rel_epsilon
else: # mode == 'max' and epsilon_mode == 'abs':
return a > best + self.threshold
def _init_is_better(self, mode, threshold, threshold_mode):
if mode not in {'min', 'max'}:
raise ValueError('mode ' + mode + ' is unknown!')
if threshold_mode not in {'rel', 'abs'}:
raise ValueError('threshold mode ' + threshold_mode + ' is unknown!')
if mode == 'min':
self.mode_worse = inf
else: # mode == 'max':
self.mode_worse = -inf
self.mode = mode
self.threshold = threshold
self.threshold_mode = threshold_mode
def state_dict(self):
return {key: value for key, value in self.__dict__.items() if key != 'optimizer'}
def load_state_dict(self, state_dict):
self.__dict__.update(state_dict)
self._init_is_better(mode=self.mode, threshold=self.threshold, threshold_mode=self.threshold_mode)
class CyclicLR(_LRScheduler):
r"""Sets the learning rate of each parameter group according to
cyclical learning rate policy (CLR). The policy cycles the learning
rate between two boundaries with a constant frequency, as detailed in
the paper `Cyclical Learning Rates for Training Neural Networks`_.
The distance between the two boundaries can be scaled on a per-iteration
or per-cycle basis.
Cyclical learning rate policy changes the learning rate after every batch.
`step` should be called after a batch has been used for training.
This class has three built-in policies, as put forth in the paper:
* "triangular": A basic triangular cycle without amplitude scaling.
* "triangular2": A basic triangular cycle that scales initial amplitude by half each cycle.
* "exp_range": A cycle that scales initial amplitude by :math:`\text{gamma}^{\text{cycle iterations}}`
at each cycle iteration.
This implementation was adapted from the github repo: `bckenstler/CLR`_
Args:
optimizer (Optimizer): Wrapped optimizer.
base_lr (float or list): Initial learning rate which is the
lower boundary in the cycle for each parameter group.