-
Notifications
You must be signed in to change notification settings - Fork 1
/
utils.py
137 lines (115 loc) · 5.07 KB
/
utils.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
""" Exponential Moving Average (EMA) of model updates
Hacked together by / Copyright 2020 Ross Wightman
"""
import logging
import numpy as np
from collections import OrderedDict
from copy import deepcopy
import torch
_logger = logging.getLogger(__name__)
class ModelEma:
""" Model Exponential Moving Average
Keep a moving average of everything in the model state_dict (parameters and buffers).
This is intended to allow functionality like
https://www.tensorflow.org/api_docs/python/tf/train/ExponentialMovingAverage
A smoothed version of the weights is necessary for some training schemes to perform well.
E.g. Google's hyper-params for training MNASNet, MobileNet-V3, EfficientNet, etc that use
RMSprop with a short 2.4-3 epoch decay period and slow LR decay rate of .96-.99 requires EMA
smoothing of weights to match results. Pay attention to the decay constant you are using
relative to your update count per epoch.
To keep EMA from using GPU resources, set device='cpu'. This will save a bit of memory but
disable validation of the EMA weights. Validation will have to be done manually in a separate
process, or after the training stops converging.
This class is sensitive where it is initialized in the sequence of model init,
GPU assignment and distributed training wrappers.
I've tested with the sequence in my own train.py for torch.DataParallel, apex.DDP, and single-GPU.
"""
def __init__(self, model, decay=0.9999, device='', resume=''):
# make a copy of the model for accumulating moving average of weights
self.ema = deepcopy(model)
self.ema.eval()
self.decay = decay
self.device = device # perform ema on different device from model if set
if device:
self.ema.to(device=device)
self.ema_has_module = hasattr(self.ema, 'module')
if resume:
self._load_checkpoint(resume)
for p in self.ema.parameters():
p.requires_grad_(False)
def _load_checkpoint(self, checkpoint_path):
checkpoint = torch.load(checkpoint_path, map_location='cpu')
assert isinstance(checkpoint, dict)
if 'state_dict_ema' in checkpoint:
new_state_dict = OrderedDict()
for k, v in checkpoint['state_dict_ema'].items():
# ema model may have been wrapped by DataParallel, and need module prefix
if self.ema_has_module:
name = 'module.' + k if not k.startswith('module') else k
else:
name = k
new_state_dict[name] = v
self.ema.load_state_dict(new_state_dict)
_logger.info("Loaded state_dict_ema")
else:
_logger.warning("Failed to find state_dict_ema, starting from loaded model weights")
def update(self, model):
# correct a mismatch in state dict keys
needs_module = hasattr(model, 'module') and not self.ema_has_module
with torch.no_grad():
msd = model.state_dict()
for k, ema_v in self.ema.state_dict().items():
if needs_module:
k = 'module.' + k
model_v = msd[k].detach()
if self.device:
model_v = model_v.to(device=self.device)
ema_v.copy_(ema_v * self.decay + (1. - self.decay) * model_v)
class AverageMeter(object):
"""Computes and stores the average and current value"""
def __init__(self, name, fmt=':f'):
self.name = name
self.fmt = fmt
self.reset()
def reset(self):
self.val = 0
self.avg = 0
self.sum = 0
self.count = 0
def update(self, val, n=1):
self.val = val
self.sum += val * n
self.count += n
self.avg = self.sum / self.count
def __str__(self):
fmtstr = '{name} {val' + self.fmt + '} ({avg' + self.fmt + '})'
return fmtstr.format(**self.__dict__)
class ToNumpy:
def __call__(self, pil_img):
np_img = np.array(pil_img, dtype=np.uint8)
if np_img.ndim < 3:
np_img = np.expand_dims(np_img, axis=-1)
np_img = np.rollaxis(np_img, 2) # HWC to CHW
return np_img
class Lighting(object):
"""Lighting noise(AlexNet - style PCA - based noise)"""
def __init__(self, alphastd, eigval, eigvec):
self.alphastd = alphastd
self.eigval = eigval
self.eigvec = eigvec
def __call__(self, img):
if self.alphastd == 0:
return img
alpha = img.new().resize_(3).normal_(0, self.alphastd)
rgb = self.eigvec.type_as(img).clone()\
.mul(alpha.view(1, 3).expand(3, 3))\
.mul(self.eigval.view(1, 3).expand(3, 3))\
.sum(1).squeeze()
return img.add(rgb.view(3, 1, 1).expand_as(img))
def make_divisible(v, divisor=8, min_value=None, round_limit=.9):
min_value = min_value or divisor
new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
# Make sure that round down does not go down by more than 10%.
if new_v < round_limit * v:
new_v += divisor
return new_v