forked from changlin31/BossNAS
-
Notifications
You must be signed in to change notification settings - Fork 0
/
utils.py
312 lines (263 loc) · 10.2 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
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
# Copyright (c) 2015-present, Facebook, Inc.
# All rights reserved.
#
# This source code is licensed under the CC-by-NC license found in the
# LICENSE file in the root directory of this source tree.
#
"""
Misc functions, including distributed helpers.
Mostly copy-paste from torchvision references.
"""
import datetime
import io
import os
import time
import torch
import torch.distributed as dist
from collections import defaultdict, deque
import logging
from collections import OrderedDict
from copy import deepcopy
_logger = logging.getLogger(__name__)
class SmoothedValue(object):
"""Track a series of values and provide access to smoothed values over a
window or the global series average.
"""
def __init__(self, window_size=20, fmt=None):
if fmt is None:
fmt = "{median:.4f} ({global_avg:.4f})"
self.deque = deque(maxlen=window_size)
self.total = 0.0
self.count = 0
self.fmt = fmt
def update(self, value, n=1):
self.deque.append(value)
self.count += n
self.total += value * n
def synchronize_between_processes(self):
"""
Warning: does not synchronize the deque!
"""
if not is_dist_avail_and_initialized():
return
t = torch.tensor([self.count, self.total], dtype=torch.float64, device='cuda')
dist.barrier()
dist.all_reduce(t)
t = t.tolist()
self.count = int(t[0])
self.total = t[1]
@property
def median(self):
d = torch.tensor(list(self.deque))
return d.median().item()
@property
def avg(self):
d = torch.tensor(list(self.deque), dtype=torch.float32)
return d.mean().item()
@property
def global_avg(self):
return self.total / self.count
@property
def max(self):
return max(self.deque)
@property
def value(self):
return self.deque[-1]
def __str__(self):
return self.fmt.format(
median=self.median,
avg=self.avg,
global_avg=self.global_avg,
max=self.max,
value=self.value)
class MetricLogger(object):
def __init__(self, delimiter="\t"):
self.meters = defaultdict(SmoothedValue)
self.delimiter = delimiter
def update(self, **kwargs):
for k, v in kwargs.items():
if isinstance(v, torch.Tensor):
v = v.item()
assert isinstance(v, (float, int))
self.meters[k].update(v)
def __getattr__(self, attr):
if attr in self.meters:
return self.meters[attr]
if attr in self.__dict__:
return self.__dict__[attr]
raise AttributeError("'{}' object has no attribute '{}'".format(
type(self).__name__, attr))
def __str__(self):
loss_str = []
for name, meter in self.meters.items():
loss_str.append(
"{}: {}".format(name, str(meter))
)
return self.delimiter.join(loss_str)
def synchronize_between_processes(self):
for meter in self.meters.values():
meter.synchronize_between_processes()
def add_meter(self, name, meter):
self.meters[name] = meter
def log_every(self, iterable, print_freq, header=None):
i = 0
if not header:
header = ''
start_time = time.time()
end = time.time()
iter_time = SmoothedValue(fmt='{avg:.4f}')
data_time = SmoothedValue(fmt='{avg:.4f}')
space_fmt = ':' + str(len(str(len(iterable)))) + 'd'
log_msg = [
header,
'[{0' + space_fmt + '}/{1}]',
'eta: {eta}',
'{meters}',
'time: {time}',
'data: {data}'
]
if torch.cuda.is_available():
log_msg.append('max mem: {memory:.0f}')
log_msg = self.delimiter.join(log_msg)
MB = 1024.0 * 1024.0
for obj in iterable:
data_time.update(time.time() - end)
yield obj
iter_time.update(time.time() - end)
if i % print_freq == 0 or i == len(iterable) - 1:
eta_seconds = iter_time.global_avg * (len(iterable) - i)
eta_string = str(datetime.timedelta(seconds=int(eta_seconds)))
if torch.cuda.is_available():
print(log_msg.format(
i, len(iterable), eta=eta_string,
meters=str(self),
time=str(iter_time), data=str(data_time),
memory=torch.cuda.max_memory_allocated() / MB))
else:
print(log_msg.format(
i, len(iterable), eta=eta_string,
meters=str(self),
time=str(iter_time), data=str(data_time)))
i += 1
end = time.time()
total_time = time.time() - start_time
total_time_str = str(datetime.timedelta(seconds=int(total_time)))
print('{} Total time: {} ({:.4f} s / it)'.format(
header, total_time_str, total_time / len(iterable)))
def _load_checkpoint_for_ema(model_ema, checkpoint):
"""
Workaround for ModelEma._load_checkpoint to accept an already-loaded object
"""
mem_file = io.BytesIO()
torch.save(checkpoint, mem_file)
mem_file.seek(0)
model_ema._load_checkpoint(mem_file)
def setup_for_distributed(is_master):
"""
This function disables printing when not in master process
"""
import builtins as __builtin__
builtin_print = __builtin__.print
def print(*args, **kwargs):
force = kwargs.pop('force', False)
if is_master or force:
builtin_print(*args, **kwargs)
__builtin__.print = print
def is_dist_avail_and_initialized():
if not dist.is_available():
return False
if not dist.is_initialized():
return False
return True
def get_world_size():
if not is_dist_avail_and_initialized():
return 1
return dist.get_world_size()
def get_rank():
if not is_dist_avail_and_initialized():
return 0
return dist.get_rank()
def is_main_process():
return get_rank() == 0
def save_on_master(*args, **kwargs):
if is_main_process():
torch.save(*args, **kwargs)
def init_distributed_mode(args):
if 'RANK' in os.environ and 'WORLD_SIZE' in os.environ:
args.rank = int(os.environ["RANK"])
args.world_size = int(os.environ['WORLD_SIZE'])
args.gpu = int(os.environ['LOCAL_RANK'])
elif 'SLURM_PROCID' in os.environ:
args.rank = int(os.environ['SLURM_PROCID'])
args.gpu = args.rank % torch.cuda.device_count()
else:
print('Not using distributed mode')
args.distributed = False
return
args.distributed = True
torch.cuda.set_device(args.gpu)
args.dist_backend = 'nccl'
print('| distributed init (rank {}): {}'.format(
args.rank, args.dist_url), flush=True)
torch.distributed.init_process_group(backend=args.dist_backend, init_method=args.dist_url,
world_size=args.world_size, rank=args.rank)
torch.distributed.barrier()
setup_for_distributed(args.rank == 0)
class ModelEma:
""" Model Exponential Moving Average (DEPRECATED)
Keep a moving average of everything in the model state_dict (parameters and buffers).
This version is deprecated, it does not work with scripted models. Will be removed eventually.
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.
"""
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 'model_ema' in checkpoint:
new_state_dict = OrderedDict()
for k, v in checkpoint['model_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)