-
Notifications
You must be signed in to change notification settings - Fork 93
/
main.py
357 lines (290 loc) · 12.6 KB
/
main.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
import argparse
import time
import yaml
import torch
import torch.backends.cudnn as cudnn
import torch.nn as nn
import torch.nn.parallel
import torch.optim
import torch.utils.data
import torchvision.datasets as datasets
import torchvision.transforms as transforms
from utils.profile import count_params
from utils.data_aug import ColorAugmentation
import os
from torch.autograd.variable import Variable
import models
model_names = sorted(name for name in models.__dict__
if name.islower() and not name.startswith("__")
and callable(models.__dict__[name]))
parser = argparse.ArgumentParser(description='PyTorch ImageNet Training')
parser.add_argument('data', metavar='DIR', help='path to dataset')
parser.add_argument('--arch', '-a', metavar='ARCH', default='resnet18',
choices=model_names,
help='models architecture: ' +
' | '.join(model_names) +
' (default: resnet18)')
parser.add_argument('--config', default='cfgs/local_test.yaml')
parser.add_argument('-j', '--workers', default=4, type=int, metavar='N',
help='number of data loading workers (default: 4)')
parser.add_argument('--epochs', default=100, type=int, metavar='N',
help='number of total epochs to run')
parser.add_argument('--start-epoch', default=0, type=int, metavar='N',
help='manual epoch number (useful on restarts)')
parser.add_argument('-b', '--batch-size', default=32, type=int,
metavar='N', help='mini-batch size (default: 256)')
parser.add_argument('--lr', '--learning-rate', default=0.1, type=float,
metavar='LR', help='initial learning rate')
parser.add_argument('--momentum', default=0.9, type=float, metavar='M',
help='momentum')
parser.add_argument('--weight-decay', '--wd', default=1e-4, type=float,
metavar='W', help='weight decay (default: 1e-4)')
parser.add_argument('--print-freq', '-p', default=10, type=int,
metavar='N', help='print frequency (default: 10)')
parser.add_argument('--resume', default='', type=str, metavar='PATH',
help='path to latest checkpoint (default: none)')
parser.add_argument('-e', '--evaluate', dest='evaluate', action='store_true',
help='evaluate models on validation set')
parser.add_argument('--train_image_list', default='', type=str, help='path to train image list')
parser.add_argument('--input_size', default=224, type=int, help='img crop size')
parser.add_argument('--image_size', default=256, type=int, help='ori img size')
parser.add_argument('--model_name', default='', type=str, help='name of the models')
best_prec1 = 0
model_names = sorted(name for name in models.__dict__
if name.islower() and not name.startswith("__")
and callable(models.__dict__[name]))
USE_GPU = torch.cuda.is_available()
def main():
global args, best_prec1, USE_GPU
args = parser.parse_args()
with open(args.config) as f:
config = yaml.load(f)
for k, v in config['common'].items():
setattr(args, k, v)
# create models
if args.input_size != 224 or args.image_size != 256:
image_size = args.image_size
input_size = args.input_size
else:
image_size = 256
input_size = 224
print("Input image size: {}, test size: {}".format(image_size, input_size))
if "model" in config.keys():
model = models.__dict__[args.arch](**config['model'])
else:
model = models.__dict__[args.arch]()
if USE_GPU:
model = model.cuda()
model = torch.nn.DataParallel(model)
count_params(model)
# define loss function (criterion) and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), args.lr, momentum=args.momentum,
weight_decay=args.weight_decay)
# optionally resume from a checkpoint
if args.resume:
if os.path.isfile(args.resume):
print("=> loading checkpoint '{}'".format(args.resume))
checkpoint = torch.load(args.resume)
best_prec1 = checkpoint['best_prec1']
model.load_state_dict(checkpoint['state_dict'])
optimizer.load_state_dict(checkpoint['optimizer'])
else:
print("=> no checkpoint found at '{}'".format(args.resume))
cudnn.benchmark = True
# Data loading code
traindir = os.path.join(args.data, 'train')
valdir = os.path.join(args.data, 'val')
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
img_size = args.input_size
ratio = 224.0 / float(img_size)
train_dataset = datasets.ImageFolder(
traindir,
transforms.Compose([
transforms.RandomResizedCrop(img_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
ColorAugmentation(),
normalize,
]))
val_dataset = datasets.ImageFolder(valdir, transforms.Compose([
transforms.Resize(int(256 * ratio)),
transforms.CenterCrop(img_size),
transforms.ToTensor(),
normalize,
]))
# if args.distributed:
# train_sampler = torch.utils.data.distributed.DistributedSampler(train_dataset)
# val_sampler = torch.utils.data.distributed.DistributedSampler(val_dataset)
# else:
train_sampler = None
val_sampler = None
train_loader = torch.utils.data.DataLoader(
train_dataset, batch_size=args.batch_size, shuffle=(train_sampler is None),
num_workers=args.workers, pin_memory=(train_sampler is None), sampler=train_sampler)
val_loader = torch.utils.data.DataLoader(val_dataset, batch_size=args.batch_size, shuffle=False,
num_workers=args.workers, pin_memory=True, sampler=val_sampler)
if args.evaluate:
validate(val_loader, model, criterion)
return
for epoch in range(args.start_epoch, args.epochs):
# if args.distributed:
# train_sampler.set_epoch(epoch)
adjust_learning_rate(optimizer, epoch)
# train for one epoch
train(train_loader, model, criterion, optimizer, epoch)
# evaluate on validation set
prec1 = validate(val_loader, model, criterion)
# remember best prec@1 and save checkpoint
is_best = prec1 > best_prec1
best_prec1 = max(prec1, best_prec1)
if not os.path.exists(args.save_path):
os.mkdir(args.save_path)
save_name = '{}/{}_{}_best.pth.tar'.format(args.save_path, args.model_name, epoch) if is_best else\
'{}/{}_{}.pth.tar'.format(args.save_path, args.model_name, epoch)
save_checkpoint({
'epoch': epoch + 1,
'arch': args.arch,
'state_dict': model.state_dict(),
'best_prec1': best_prec1,
'optimizer': optimizer.state_dict(),
}, filename=save_name)
def train(train_loader, model, criterion, optimizer, epoch):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
top1 = AverageMeter()
top5 = AverageMeter()
# 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)
# pytorch 0.4.0 compatible
if '0.4.' in torch.__version__:
if USE_GPU:
input_var = torch.cuda.FloatTensor(input.cuda())
target_var = torch.cuda.LongTensor(target.cuda())
else:
input_var = torch.FloatTensor(input)
target_var = torch.LongTensor(target)
else: # pytorch 0.3.1 or less compatible
if USE_GPU:
input = input.cuda()
target = target.cuda(async=True)
input_var = Variable(input)
target_var = Variable(target)
# compute output
output = model(input_var)
loss = criterion(output, target_var)
prec1, prec5 = accuracy(output.data, target_var, topk=(1, 5))
# measure accuracy and record loss
reduced_prec1 = prec1.clone()
reduced_prec5 = prec5.clone()
top1.update(reduced_prec1[0])
top5.update(reduced_prec5[0])
reduced_loss = loss.data.clone()
losses.update(reduced_loss)
# compute gradient and do SGD step
optimizer.zero_grad()
loss.backward()
# check whether the network is well connected
optimizer.step()
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if i % args.print_freq == 0:
with open('logs/{}_{}.log'.format(time_stp, args.arch), 'a+') as flog:
line = 'Epoch: [{0}][{1}/{2}]\t ' \
'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t' \
'Loss {loss.val:.4f} ({loss.avg:.4f})\t' \
'Prec@1 {top1.val:.3f} ({top1.avg:.3f})\t' \
'Prec@5 {top5.val:.3f} ({top5.avg:.3f})'.format(epoch, i, len(train_loader),
batch_time=batch_time, loss=losses, top1=top1, top5=top5)
print(line)
flog.write('{}\n'.format(line))
def validate(val_loader, model, criterion):
global time_stp
batch_time = AverageMeter()
losses = AverageMeter()
top1 = AverageMeter()
top5 = AverageMeter()
# switch to evaluate mode
model.eval()
end = time.time()
for i, (input, target) in enumerate(val_loader):
# pytorch 0.4.0 compatible
if '0.4.' in torch.__version__:
with torch.no_grad():
if USE_GPU:
input_var = torch.cuda.FloatTensor(input.cuda())
target_var = torch.cuda.LongTensor(target.cuda())
else:
input_var = torch.FloatTensor(input)
target_var = torch.LongTensor(target)
else: # pytorch 0.3.1 or less compatible
if USE_GPU:
input = input.cuda()
target = target.cuda(async=True)
input_var = Variable(input, volatile=True)
target_var = Variable(target, volatile=True)
# compute output
output = model(input_var)
loss = criterion(output, target_var)
# measure accuracy and record loss
prec1, prec5 = accuracy(output.data, target_var, topk=(1, 5))
losses.update(loss.data, input.size(0))
top1.update(prec1[0], input.size(0))
top5.update(prec5[0], input.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if i % args.print_freq == 0:
line = 'Test: [{0}/{1}]\t' \
'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t' \
'Loss {loss.val:.4f} ({loss.avg:.4f})\t' \
'Prec@1 {top1.val:.3f} ({top1.avg:.3f})\t' \
'Prec@5 {top5.val:.3f} ({top5.avg:.3f})'.format(i, len(val_loader), batch_time=batch_time,
loss=losses, top1=top1, top5=top5)
with open('logs/{}_{}.log'.format(time_stp, args.arch), 'a+') as flog:
flog.write('{}\n'.format(line))
print(line)
return top1.avg
def save_checkpoint(state, filename='checkpoint.pth.tar'):
torch.save(state, filename)
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 adjust_learning_rate(optimizer, epoch):
"""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 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
if __name__ == '__main__':
time_stp = time.strftime("%Y-%m-%d_%H:%M:%S", time.localtime())
main()