-
Notifications
You must be signed in to change notification settings - Fork 0
/
RandWireNN_train.py
175 lines (143 loc) · 5.98 KB
/
RandWireNN_train.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
import torch
import torch.optim as optim
import time
import os, sys
def train(train_loader, model, criterion, optimizer, epoch, cfg):
batch_time = AverageMeter('Time', ':6.3f')
data_time = AverageMeter('Data', ':6.3f')
losses = AverageMeter('Loss', ':.4e')
top1 = AverageMeter('Acc@1', ':6.2f')
top5 = AverageMeter('Acc@5', ':6.2f')
progress = ProgressMeter(len(train_loader), batch_time, data_time, losses, top1,
top5, prefix="Epoch: [{}]".format(epoch))
# switch to train mode
model.train()
end = time.time()
for i, (input, target) in enumerate(train_loader):
# measure data loading time
data_time.update(time.time() - end)
input = input.to(cfg.DEVICE)
target = target.to(cfg.DEVICE)
# compute output
optimizer.zero_grad()
output = model(input)
loss = criterion(output, target)
# measure accuracy and record loss
acc1, acc5 = accuracy(output, target, topk=(1, 5))
losses.update(loss.item(), input.size(0))
top1.update(acc1[0], input.size(0))
top5.update(acc5[0], input.size(0))
# compute gradient and do SGD step
loss.backward()
optimizer.step()
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if i % cfg.PRINT_FREQ == 0:
progress.print(i)
if cfg.VISDOM:
cfg.vis.line(X=torch.Tensor([epoch+(i/len(train_loader))]).unsqueeze(0).cpu(),
Y=torch.Tensor([loss]).unsqueeze(0).cpu(),
env='torch',win=cfg.loss_window,name='train_loss',update='append')
# for check lr_scheduler
# for param_group in optimizer.param_groups:
# print(param_group['lr'])
if i % cfg.SAVE_FREQ == 0:
torch.save(model.state_dict(), './output/model/%s_%03d_%02d.cpt' % (cfg.DATASET_NAME, epoch, int(i)/1000))
def validate(val_loader, model, criterion, cfg):
batch_time = AverageMeter('Time', ':6.3f')
losses = AverageMeter('Loss', ':.4e')
top1 = AverageMeter('Acc@1', ':6.2f')
top5 = AverageMeter('Acc@5', ':6.2f')
progress = ProgressMeter(len(val_loader), batch_time, losses, top1, top5,
prefix='Test: ')
# switch to evaluate mode
model.eval()
with torch.no_grad():
end = time.time()
for i, (input, target) in enumerate(val_loader):
input = input.to(cfg.DEVICE)
target = target.to(cfg.DEVICE)
# compute output
output = model(input)
loss = criterion(output, target)
# measure accuracy and record loss
acc1, acc5 = accuracy(output, target, topk=(1, 5))
losses.update(loss.item(), input.size(0))
top1.update(acc1[0], input.size(0))
top5.update(acc5[0], input.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if i % cfg.PRINT_FREQ == 0:
progress.print(i)
# TODO: this should also be done with the ProgressMeter
print(' * Acc@1 {top1.avg:.3f} Acc@5 {top5.avg:.3f}'
.format(top1=top1, top5=top5))
return losses.avg, top1.avg
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 ProgressMeter(object):
def __init__(self, num_batches, *meters, prefix=""):
self.batch_fmtstr = self._get_batch_fmtstr(num_batches)
self.meters = meters
self.prefix = prefix
def print(self, batch):
entries = [self.prefix + self.batch_fmtstr.format(batch)]
entries += [str(meter) for meter in self.meters]
print('\t'.join(entries))
def _get_batch_fmtstr(self, num_batches):
num_digits = len(str(num_batches // 1))
fmt = '{:' + str(num_digits) + 'd}'
return '[' + fmt + '/' + fmt.format(num_batches) + ']'
def adjust_learning_rate(optimizer, epoch, args):
"""Sets the learning rate to the initial LR decayed by 10 every 30 epochs"""
lr = args.lr * (0.1 ** (epoch // 30))
for param_group in optimizer.param_groups:
param_group['lr'] = lr
def accuracy(output, target, topk=(1,)):
"""Computes the accuracy over the k top predictions for the specified values of k"""
with torch.no_grad():
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 prepare(cfg, use_arg_parser=True):
if not os.path.isdir("./output/"):
os.mkdir("./output/")
if not os.path.isdir("./output/model"):
os.mkdir("./output/model")
if not os.path.isdir("./output/graph"):
os.mkdir("./output/graph")
if not cfg.TEST_MODE:
if cfg.VISDOM:
cfg.loss_window = cfg.vis.line(
Y=torch.zeros((1)).cpu(),
X=torch.zeros((1)).cpu(),env='torch',
opts=dict(xlabel='epoch',ylabel='Loss',
title=cfg.DATASET_NAME+"_"
+time.strftime("%m/%d %H:%M", time.localtime()),
legend=['train_loss','val_loss']))