-
Notifications
You must be signed in to change notification settings - Fork 49
/
train_imagenet.py
438 lines (378 loc) · 12.1 KB
/
train_imagenet.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
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
import argparse
import os
import random
import shutil
import time
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.models as models
import torchvision.transforms as transforms
from MODELS.mobilenet import *
from MODELS.resnet import *
from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True
model_names = sorted(
name
for name in models.__dict__
if name.islower() and not name.startswith("__") and callable(models.__dict__[name])
)
import wandb
wandb.init(project="TripletAttention")
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="resnet",
help="model architecture: " + " | ".join(model_names) + " (default: resnet18)",
)
parser.add_argument("--depth", default=50, type=int, metavar="D", help="model depth")
parser.add_argument(
"--ngpu", default=4, type=int, metavar="G", help="number of gpus to use"
)
parser.add_argument(
"-j",
"--workers",
default=4,
type=int,
metavar="N",
help="number of data loading workers (default: 4)",
)
parser.add_argument(
"--epochs", default=90, 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=256,
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(
"--seed",
type=int,
default=1234,
metavar="BS",
help="input batch size for training (default: 64)",
)
parser.add_argument(
"--prefix",
type=str,
required=True,
metavar="PFX",
help="prefix for logging & checkpoint saving",
)
parser.add_argument(
"--evaluate", dest="evaluate", action="store_true", help="evaluation only"
)
parser.add_argument("--att-type", type=str, choices=["TripletAttention"], default=None)
best_prec1 = 0
if not os.path.exists("./checkpoints"):
os.mkdir("./checkpoints")
def main():
global args, best_prec1
global viz, train_lot, test_lot
args = parser.parse_args()
print("args", args)
torch.manual_seed(args.seed)
torch.cuda.manual_seed_all(args.seed)
random.seed(args.seed)
# create model
if args.arch == "resnet":
model = ResidualNet("ImageNet", args.depth, 1000, args.att_type)
elif args.arch == "mobilenet":
model = triplet_attention_mobilenet_v2()
# define loss function (criterion) and optimizer
criterion = nn.CrossEntropyLoss().cuda()
optimizer = torch.optim.SGD(
model.parameters(),
args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay,
)
model = torch.nn.DataParallel(model, device_ids=list(range(args.ngpu)))
# model = torch.nn.DataParallel(model).cuda()
wandb.watch(model)
model = model.cuda()
# print ("model")
# print (model)
# get the number of model parameters
print(
"Number of model parameters: {}".format(
sum([p.data.nelement() for p in model.parameters()])
)
)
wandb.log({"parameters": sum([p.data.nelement() for p in model.parameters()])})
# 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)
args.start_epoch = checkpoint["epoch"]
best_prec1 = checkpoint["best_prec1"]
model.load_state_dict(checkpoint["state_dict"])
if "optimizer" in checkpoint:
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 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]
)
# import pdb
# pdb.set_trace()
val_loader = torch.utils.data.DataLoader(
datasets.ImageFolder(
valdir,
transforms.Compose(
[
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
normalize,
]
),
),
batch_size=args.batch_size,
shuffle=False,
num_workers=args.workers,
pin_memory=True,
)
if args.evaluate:
validate(val_loader, model, criterion, 0)
return
train_dataset = datasets.ImageFolder(
traindir,
transforms.Compose(
[
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
normalize,
]
),
)
train_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=True,
sampler=train_sampler,
)
for epoch in range(args.start_epoch, args.epochs):
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, epoch)
# remember 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.prefix,
)
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)
target = target.cuda(non_blocking=True)
input_var = torch.autograd.Variable(input)
target_var = torch.autograd.Variable(target)
# compute output
output = model(input_var)
loss = criterion(output, target_var)
# measure accuracy and record loss
prec1, prec5 = accuracy(output.data, target, topk=(1, 5))
losses.update(loss.data.item(), input.size(0))
top1.update(prec1.item(), input.size(0))
top5.update(prec5.item(), 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 % args.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})".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, epoch):
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(non_blocking=True)
input_var = torch.autograd.Variable(input, volatile=True)
target_var = torch.autograd.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, topk=(1, 5))
losses.update(loss.data.item(), input.size(0))
top1.update(prec1.item(), input.size(0))
top5.update(prec5.item(), input.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if i % args.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))
# log stats to wandb
wandb.log(
{
"epoch": epoch,
"Top-1 accuracy": top1.avg,
"Top-5 accuracy": top5.avg,
"loss": losses.avg,
}
)
return top1.avg
def save_checkpoint(state, is_best, prefix):
filename = "./checkpoints/%s_checkpoint.pth.tar" % prefix
torch.save(state, filename)
if is_best:
shutil.copyfile(filename, "./checkpoints/%s_model_best.pth.tar" % prefix)
wandb.save(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"""
if args.arch == "mobilenet":
lr = args.lr * (0.98 ** epoch)
elif args.arch == "resnet":
lr = args.lr * (0.1 ** (epoch // 30))
for param_group in optimizer.param_groups:
param_group["lr"] = lr
wandb.log({"lr": lr})
def accuracy(output, target, topk=(1,)):
"""Computes the precision@k 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
if __name__ == "__main__":
main()