-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathtrain.py
184 lines (147 loc) · 6.99 KB
/
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
176
177
178
179
180
181
182
183
184
r"""PyTorch Detection Training.
To run in a multi-gpu environment, use the distributed launcher::
python -m torch.distributed.launch --nproc_per_node=$NGPU --use_env \
train.py ... --world-size $NGPU
"""
import datetime
import os
import time
import torch
import torch.utils.data
from torch import nn
import torchvision
import torchvision.models.detection
import torchvision.models.detection.mask_rcnn
from coco_utils import get_coco, get_coco_kp
from group_by_aspect_ratio import GroupedBatchSampler, create_aspect_ratio_groups
from engine import train_one_epoch, evaluate
import utils
import transforms as T
def get_dataset(name, image_set, transform, data_path):
paths = {
"coco": (data_path, get_coco, 91),
"coco_kp": (data_path, get_coco_kp, 2)
}
p, ds_fn, num_classes = paths[name]
ds = ds_fn(p, image_set=image_set, transforms=transform)
return ds, num_classes
def get_transform(train):
transforms = []
transforms.append(T.ToTensor())
if train:
transforms.append(T.RandomHorizontalFlip(0.5))
return T.Compose(transforms)
def main(args):
utils.init_distributed_mode(args)
print(args)
device = torch.device(args.device)
# Data loading code
print("Loading data")
dataset, num_classes = get_dataset(args.dataset, "train", get_transform(train=True), args.data_path)
dataset_test, _ = get_dataset(args.dataset, "val", get_transform(train=False), args.data_path)
print("Creating data loaders")
if args.distributed:
train_sampler = torch.utils.data.distributed.DistributedSampler(dataset)
test_sampler = torch.utils.data.distributed.DistributedSampler(dataset_test)
else:
train_sampler = torch.utils.data.RandomSampler(dataset)
test_sampler = torch.utils.data.SequentialSampler(dataset_test)
if args.aspect_ratio_group_factor >= 0:
group_ids = create_aspect_ratio_groups(dataset, k=args.aspect_ratio_group_factor)
train_batch_sampler = GroupedBatchSampler(train_sampler, group_ids, args.batch_size)
else:
train_batch_sampler = torch.utils.data.BatchSampler(
train_sampler, args.batch_size, drop_last=True)
data_loader = torch.utils.data.DataLoader(
dataset, batch_sampler=train_batch_sampler, num_workers=args.workers,
collate_fn=utils.collate_fn)
data_loader_test = torch.utils.data.DataLoader(
dataset_test, batch_size=1,
sampler=test_sampler, num_workers=args.workers,
collate_fn=utils.collate_fn)
print("Creating model")
model = torchvision.models.detection.__dict__[args.model](num_classes=num_classes,
pretrained=args.pretrained)
model.to(device)
model_without_ddp = model
if args.distributed:
model = torch.nn.parallel.DistributedDataParallel(model, device_ids=[args.gpu])
model_without_ddp = model.module
params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.SGD(
params, lr=args.lr, momentum=args.momentum, weight_decay=args.weight_decay)
# lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=args.lr_step_size, gamma=args.lr_gamma)
lr_scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, milestones=args.lr_steps, gamma=args.lr_gamma)
if args.resume:
checkpoint = torch.load(args.resume, map_location='cpu')
model_without_ddp.load_state_dict(checkpoint['model'])
optimizer.load_state_dict(checkpoint['optimizer'])
lr_scheduler.load_state_dict(checkpoint['lr_scheduler'])
if args.test_only:
evaluate(model, data_loader_test, device=device)
return
print("Start training")
start_time = time.time()
for epoch in range(args.epochs):
if args.distributed:
train_sampler.set_epoch(epoch)
train_one_epoch(model, optimizer, data_loader, device, epoch, args.print_freq)
lr_scheduler.step()
if args.output_dir:
utils.save_on_master({
'model': model_without_ddp.state_dict(),
'optimizer': optimizer.state_dict(),
'lr_scheduler': lr_scheduler.state_dict(),
'args': args},
os.path.join(args.output_dir, 'model_{}.pth'.format(epoch)))
# evaluate after every epoch
evaluate(model, data_loader_test, device=device)
total_time = time.time() - start_time
total_time_str = str(datetime.timedelta(seconds=int(total_time)))
print('Training time {}'.format(total_time_str))
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser(
description=__doc__)
parser.add_argument('--data-path', default='/datasets01/COCO/022719/', help='dataset')
parser.add_argument('--dataset', default='coco', help='dataset')
parser.add_argument('--model', default='maskrcnn_resnet50_fpn', help='model')
parser.add_argument('--device', default='cuda', help='device')
parser.add_argument('-b', '--batch-size', default=2, type=int)
parser.add_argument('--epochs', default=13, type=int, metavar='N',
help='number of total epochs to run')
parser.add_argument('-j', '--workers', default=4, type=int, metavar='N',
help='number of data loading workers (default: 16)')
parser.add_argument('--lr', default=0.02, type=float, help='initial learning rate')
parser.add_argument('--momentum', default=0.9, type=float, metavar='M',
help='momentum')
parser.add_argument('--wd', '--weight-decay', default=1e-4, type=float,
metavar='W', help='weight decay (default: 1e-4)',
dest='weight_decay')
parser.add_argument('--lr-step-size', default=8, type=int, help='decrease lr every step-size epochs')
parser.add_argument('--lr-steps', default=[8, 11], nargs='+', type=int, help='decrease lr every step-size epochs')
parser.add_argument('--lr-gamma', default=0.1, type=float, help='decrease lr by a factor of lr-gamma')
parser.add_argument('--print-freq', default=20, type=int, help='print frequency')
parser.add_argument('--output-dir', default='.', help='path where to save')
parser.add_argument('--resume', default='', help='resume from checkpoint')
parser.add_argument('--aspect-ratio-group-factor', default=0, type=int)
parser.add_argument(
"--test-only",
dest="test_only",
help="Only test the model",
action="store_true",
)
parser.add_argument(
"--pretrained",
dest="pretrained",
help="Use pre-trained models from the modelzoo",
action="store_true",
)
# distributed training parameters
parser.add_argument('--world-size', default=1, type=int,
help='number of distributed processes')
parser.add_argument('--dist-url', default='env://', help='url used to set up distributed training')
args = parser.parse_args()
if args.output_dir:
utils.mkdir(args.output_dir)
main(args)