-
Notifications
You must be signed in to change notification settings - Fork 81
/
main.py
252 lines (211 loc) · 9.46 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
import argparse
import os
import time
import torch
import torch.nn as nn
import torch.optim as optim
import torch.utils.data
from models import *
from data_loader import data_loader
from helper import AverageMeter, save_checkpoint, accuracy, adjust_learning_rate
model_names = [
'alexnet', 'squeezenet1_0', 'squeezenet1_1', 'densenet121',
'densenet169', 'densenet201', 'densenet201', 'densenet161',
'vgg11', 'vgg11_bn', 'vgg13', 'vgg13_bn', 'vgg16', 'vgg16_bn',
'vgg19', 'vgg19_bn', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
'resnet152'
]
parser = argparse.ArgumentParser(description='PyTorch ImageNet Training')
parser.add_argument('data', metavar='DIR', help='path to dataset')
parser.add_argument('-a', '--arch', metavar='ARCH', default='alexnet', choices=model_names,
help='model architecture: ' + ' | '.join(model_names) + ' (default: alexnet)')
parser.add_argument('--epochs', default=90, type=int, metavar='N',
help='numer of total epochs to run')
parser.add_argument('--start-epoch', default=0, type=int, metavar='N',
help='manual epoch number (useful to restarts)')
parser.add_argument('-b', '--batch-size', default=256, type=int, metavar='N',
help='mini-batch size (default: 256)')
parser.add_argument('--lr', '--learning-rate', default=0.01, 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('-j', '--workers', default=4, type=int, metavar='N',
help='number of data loading workers (default: 4)')
parser.add_argument('-m', '--pin-memory', dest='pin_memory', action='store_true',
help='use pin memory')
parser.add_argument('-p', '--pretrained', dest='pretrained', action='store_true',
help='use pre-trained model')
parser.add_argument('--print-freq', '-f', default=10, type=int, metavar='N',
help='print frequency (default: 10)')
parser.add_argument('--resume', default='', type=str, metavar='PATH',
help='path to latest checkpoitn, (default: None)')
parser.add_argument('-e', '--evaluate', dest='evaluate', action='store_true',
help='evaluate model on validation set')
best_prec1 = 0.0
def main():
global args, best_prec1
args = parser.parse_args()
# create model
if args.pretrained:
print("=> using pre-trained model '{}'".format(args.arch))
else:
print("=> creating model '{}'".format(args.arch))
if args.arch == 'alexnet':
model = alexnet(pretrained=args.pretrained)
elif args.arch == 'squeezenet1_0':
model = squeezenet1_0(pretrained=args.pretrained)
elif args.arch == 'squeezenet1_1':
model = squeezenet1_1(pretrained=args.pretrained)
elif args.arch == 'densenet121':
model = densenet121(pretrained=args.pretrained)
elif args.arch == 'densenet169':
model = densenet169(pretrained=args.pretrained)
elif args.arch == 'densenet201':
model = densenet201(pretrained=args.pretrained)
elif args.arch == 'densenet161':
model = densenet161(pretrained=args.pretrained)
elif args.arch == 'vgg11':
model = vgg11(pretrained=args.pretrained)
elif args.arch == 'vgg13':
model = vgg13(pretrained=args.pretrained)
elif args.arch == 'vgg16':
model = vgg16(pretrained=args.pretrained)
elif args.arch == 'vgg19':
model = vgg19(pretrained=args.pretrained)
elif args.arch == 'vgg11_bn':
model = vgg11_bn(pretrained=args.pretrained)
elif args.arch == 'vgg13_bn':
model = vgg13_bn(pretrained=args.pretrained)
elif args.arch == 'vgg16_bn':
model = vgg16_bn(pretrained=args.pretrained)
elif args.arch == 'vgg19_bn':
model = vgg19_bn(pretrained=args.pretrained)
elif args.arch == 'resnet18':
model = resnet18(pretrained=args.pretrained)
elif args.arch == 'resnet34':
model = resnet34(pretrained=args.pretrained)
elif args.arch == 'resnet50':
model = resnet50(pretrained=args.pretrained)
elif args.arch == 'resnet101':
model = resnet101(pretrained=args.pretrained)
elif args.arch == 'resnet152':
model = resnet152(pretrained=args.pretrained)
else:
raise NotImplementedError
# use cuda
model.cuda()
# model = torch.nn.parallel.DistributedDataParallel(model)
# define loss and optimizer
criterion = nn.CrossEntropyLoss().cuda()
optimizer = optim.SGD(model.parameters(), lr=args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay)
# optionlly resume from a checkpoint
if args.resume:
if os.path.isfile(args.resume):
print("=> loading checkpoint '{}'".format(args.resume))
checkpoint = torch.load(args.resume)
args.start_epoch = checkpoint['epoch']
best_prec1 = checkpoint['best_prec1']
model.load_state_dict(checkpoint['state_dict'])
optimizer.load_state_dict(checkpoint['optimizer'])
print("=> loaded checkpoint '{}' (epoch {})".format(args.resume, checkpoint['epoch']))
else:
print("=> no checkpoint found at '{}'".format(args.resume))
# cudnn.benchmark = True
# Data loading
train_loader, val_loader = data_loader(args.data, args.batch_size, args.workers, args.pin_memory)
if args.evaluate:
validate(val_loader, model, criterion, args.print_freq)
return
for epoch in range(args.start_epoch, args.epochs):
adjust_learning_rate(optimizer, epoch, args.lr)
# train for one epoch
train(train_loader, model, criterion, optimizer, epoch, args.print_freq)
# evaluate on validation set
prec1, prec5 = validate(val_loader, model, criterion, args.print_freq)
# remember the best prec@1 and save checkpoint
is_best = prec1 > best_prec1
best_prec1 = max(prec1, best_prec1)
save_checkpoint({
'epoch': epoch + 1,
'arch': args.arch,
'state_dict': model.state_dict(),
'best_prec1': best_prec1,
'optimizer': optimizer.state_dict()
}, is_best, args.arch + '.pth')
def train(train_loader, model, criterion, optimizer, epoch, print_freq):
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)
target = target.cuda(async=True)
input = input.cuda(async=True)
# compute output
output = model(input)
loss = criterion(output, target)
# measure accuracy and record loss
prec1, prec5 = accuracy(output.data, target, topk=(1, 5))
losses.update(loss.item(), input.size(0))
top1.update(prec1[0], input.size(0))
top5.update(prec1[0], input.size(0))
# compute gradient and do SGD step
optimizer.zero_grad()
loss.backward()
optimizer.step()
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if i % print_freq == 0:
print('Epoch: [{0}][{1}/{2}]\t'
'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
'Data {data_time.val:.3f} ({data_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})\t'.format(
epoch, i, len(train_loader), batch_time=batch_time,
data_time=data_time, loss=losses, top1=top1, top5=top5))
def validate(val_loader, model, criterion, print_freq):
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):
target = target.cuda(async=True)
input = input.cuda(async=True)
with torch.no_grad():
# compute output
output = model(input)
loss = criterion(output, target)
# measure accuracy and record loss
prec1, prec5 = accuracy(output.data, target, topk=(1, 5))
losses.update(loss.item(), 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 % print_freq == 0:
print('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))
print(' * Prec@1 {top1.avg:.3f} Prec@5 {top5.avg:.3f}'.format(top1=top1, top5=top5))
return top1.avg, top5.avg
if __name__ == '__main__':
main()