-
Notifications
You must be signed in to change notification settings - Fork 0
/
utils.py
226 lines (190 loc) · 7.31 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
import time
import math
import random
import numpy as np
import torch
from torch.optim.lr_scheduler import _LRScheduler
from sklearn.model_selection import StratifiedKFold
# https://github.com/kevin-ssy/FishNet/blob/master/main.py#L342
def accuracy(output, target, topk=(1,)):
"""Computes the precision@k for the specified values of k"""
maxk = max(topk)
batch_size = target.size(0)
_, pred = output.topk(maxk, 1, True, True)
pred = pred.t()
correct = pred.eq(target.view(1, -1).expand_as(pred))
res = []
for k in topk:
correct_k = correct[:k].view(-1).float().sum(0, keepdim=True)
res.append(correct_k.mul_(100.0 / batch_size))
return res
def accuracy2(outputs, labels):
_, preds = torch.max(outputs, dim=1)
return torch.tensor(torch.sum(preds == labels).item() / len(preds))
# https://www.kaggle.com/code/librauee/train-deberta-v3-large-baseline
class AverageMeter(object):
"""Computes and stores the average and current value"""
def __init__(self):
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 asMinutes(s):
m = math.floor(s / 60)
s -= m * 60
return "%dm %ds" % (m, s)
def timeSince(since, percent):
now = time.time()
s = now - since
es = s / (percent)
rs = es - s
return "%s (remain %s)" % (asMinutes(s), asMinutes(rs))
def seed_everything(seed):
torch.manual_seed(seed)
torch.cuda.manual_seed(seed)
torch.cuda.manual_seed_all(seed) # if use multi-GPU
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
np.random.seed(seed)
random.seed(seed)
def mysplit(X, y, fold, n_split, seed):
skf = StratifiedKFold(n_splits=n_split, random_state=seed, shuffle=True)
for idx, (train_idx, valid_idx) in enumerate(skf.split(X, y)):
if idx == fold:
X_train, X_valid = X[train_idx], X[valid_idx]
y_train, y_valid = y[train_idx], y[valid_idx]
return X_train, X_valid, y_train, y_valid
class EarlyStopper:
def __init__(self, patience):
self.patience = patience
self.patience_counter = 0
self.best_acc = 0
self.stop = False
self.save_model = False
def check_early_stopping(self, score):
if self.best_acc == 0:
self.best_acc = score
return None
elif score <= self.best_acc:
self.patience_counter += 1
self.save_model = False
if self.patience_counter == self.patience:
self.stop = True
elif score > self.best_acc:
self.patience_counter = 0
self.save_model = True
print("best score increased :", f"{self.best_acc} --> {score}")
self.best_acc = score
class CosineAnnealingWarmupRestarts(_LRScheduler):
"""
optimizer (Optimizer): Wrapped optimizer.
first_cycle_steps (int): First cycle step size.
cycle_mult(float): Cycle steps magnification. Default: -1.
max_lr(float): First cycle's max learning rate. Default: 0.1.
min_lr(float): Min learning rate. Default: 0.001.
warmup_steps(int): Linear warmup step size. Default: 0.
gamma(float): Decrease rate of max learning rate by cycle. Default: 1.
last_epoch (int): The index of last epoch. Default: -1.
"""
def __init__(
self,
optimizer: torch.optim.Optimizer,
first_cycle_steps: int,
cycle_mult: float = 1.0,
max_lr: float = 0.1,
min_lr: float = 0.001,
warmup_steps: int = 0,
gamma: float = 1.0,
last_epoch: int = -1,
):
assert warmup_steps < first_cycle_steps
self.first_cycle_steps = first_cycle_steps # first cycle step size
self.cycle_mult = cycle_mult # cycle steps magnification
self.base_max_lr = max_lr # first max learning rate
self.max_lr = max_lr # max learning rate in the current cycle
self.min_lr = min_lr # min learning rate
self.warmup_steps = warmup_steps # warmup step size
self.gamma = gamma # decrease rate of max learning rate by cycle
self.cur_cycle_steps = first_cycle_steps # first cycle step size
self.cycle = 0 # cycle count
self.step_in_cycle = last_epoch # step size of the current cycle
super(CosineAnnealingWarmupRestarts, self).__init__(optimizer, last_epoch)
self.init_lr()
def init_lr(self):
self.base_lrs = []
for param_group in self.optimizer.param_groups:
param_group["lr"] = self.min_lr
self.base_lrs.append(self.min_lr)
def get_lr(self):
if self.step_in_cycle == -1:
return self.base_lrs
elif self.step_in_cycle < self.warmup_steps:
return [
(self.max_lr - base_lr) * self.step_in_cycle / self.warmup_steps
+ base_lr
for base_lr in self.base_lrs
]
else:
return [
base_lr
+ (self.max_lr - base_lr)
* (
1
+ math.cos(
math.pi
* (self.step_in_cycle - self.warmup_steps)
/ (self.cur_cycle_steps - self.warmup_steps)
)
)
/ 2
for base_lr in self.base_lrs
]
def step(self, epoch=None):
if epoch is None:
epoch = self.last_epoch + 1
self.step_in_cycle = self.step_in_cycle + 1
if self.step_in_cycle >= self.cur_cycle_steps:
self.cycle += 1
self.step_in_cycle = self.step_in_cycle - self.cur_cycle_steps
self.cur_cycle_steps = (
int((self.cur_cycle_steps - self.warmup_steps) * self.cycle_mult)
+ self.warmup_steps
)
else:
if epoch >= self.first_cycle_steps:
if self.cycle_mult == 1.0:
self.step_in_cycle = epoch % self.first_cycle_steps
self.cycle = epoch // self.first_cycle_steps
else:
n = int(
math.log(
(
epoch / self.first_cycle_steps * (self.cycle_mult - 1)
+ 1
),
self.cycle_mult,
)
)
self.cycle = n
self.step_in_cycle = epoch - int(
self.first_cycle_steps
* (self.cycle_mult**n - 1)
/ (self.cycle_mult - 1)
)
self.cur_cycle_steps = self.first_cycle_steps * self.cycle_mult ** (
n
)
else:
self.cur_cycle_steps = self.first_cycle_steps
self.step_in_cycle = epoch
self.max_lr = self.base_max_lr * (self.gamma**self.cycle)
self.last_epoch = math.floor(epoch)
for param_group, lr in zip(self.optimizer.param_groups, self.get_lr()):
param_group["lr"] = lr