-
Notifications
You must be signed in to change notification settings - Fork 167
/
main.py
executable file
·207 lines (184 loc) · 7.78 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
import os
import sys
import json
import numpy as np
import torch
from torch import nn
from torch import optim
from torch.optim import lr_scheduler
from opts import parse_opts
from model import generate_model
from mean import get_mean, get_std
from spatial_transforms import *
from temporal_transforms import *
from target_transforms import ClassLabel, VideoID
from target_transforms import Compose as TargetCompose
from dataset import get_training_set, get_validation_set, get_test_set
from utils import *
from train import train_epoch
from validation import val_epoch
import test
if __name__ == '__main__':
opt = parse_opts()
if opt.root_path != '':
opt.video_path = os.path.join(opt.root_path, opt.video_path)
opt.annotation_path = os.path.join(opt.root_path, opt.annotation_path)
opt.result_path = os.path.join(opt.root_path, opt.result_path)
if not os.path.exists(opt.result_path):
os.makedirs(opt.result_path)
if opt.resume_path:
opt.resume_path = os.path.join(opt.root_path, opt.resume_path)
if opt.pretrain_path:
opt.pretrain_path = os.path.join(opt.root_path, opt.pretrain_path)
opt.scales = [opt.initial_scale]
for i in range(1, opt.n_scales):
opt.scales.append(opt.scales[-1] * opt.scale_step)
opt.arch = '{}'.format(opt.model)
opt.mean = get_mean(opt.norm_value, dataset=opt.mean_dataset)
opt.std = get_std(opt.norm_value)
opt.store_name = '_'.join([opt.dataset, opt.model, str(opt.width_mult) + 'x',
opt.modality, str(opt.sample_duration)])
print(opt)
with open(os.path.join(opt.result_path, 'opts.json'), 'w') as opt_file:
json.dump(vars(opt), opt_file)
torch.manual_seed(opt.manual_seed)
model, parameters = generate_model(opt)
print(model)
# Egogesture, with "no-gesture" training, weighted loss
# class_weights = torch.cat((0.012*torch.ones([1, 83]), 0.00015*torch.ones([1, 1])), 1)
criterion = nn.CrossEntropyLoss()
# # nvgesture, with "no-gesture" training, weighted loss
# class_weights = torch.cat((0.04*torch.ones([1, 25]), 0.0008*torch.ones([1, 1])), 1)
# criterion = nn.CrossEntropyLoss(weight=class_weights, size_average=False)
# criterion = nn.CrossEntropyLoss()
if not opt.no_cuda:
criterion = criterion.cuda()
if opt.no_mean_norm and not opt.std_norm:
norm_method = Normalize([0, 0, 0], [1, 1, 1])
elif not opt.std_norm:
norm_method = Normalize(opt.mean, [1, 1, 1])
else:
norm_method = Normalize(opt.mean, opt.std)
if not opt.no_train:
assert opt.train_crop in ['random', 'corner', 'center']
if opt.train_crop == 'random':
crop_method = MultiScaleRandomCrop(opt.scales, opt.sample_size)
elif opt.train_crop == 'corner':
crop_method = MultiScaleCornerCrop(opt.scales, opt.sample_size)
elif opt.train_crop == 'center':
crop_method = MultiScaleCornerCrop(
opt.scales, opt.sample_size, crop_positions=['c'])
spatial_transform = Compose([
#RandomHorizontalFlip(),
#RandomRotate(),
#RandomResize(),
crop_method,
#MultiplyValues(),
#Dropout(),
#SaltImage(),
#Gaussian_blur(),
#SpatialElasticDisplacement(),
ToTensor(opt.norm_value), norm_method
])
temporal_transform = TemporalRandomCrop(opt.sample_duration, opt.downsample)
target_transform = ClassLabel()
training_data = get_training_set(opt, spatial_transform,
temporal_transform, target_transform)
train_loader = torch.utils.data.DataLoader(
training_data,
batch_size=opt.batch_size,
shuffle=True,
num_workers=opt.n_threads,
pin_memory=True)
train_logger = Logger(
os.path.join(opt.result_path, opt.store_name + '_train.log'),
['epoch', 'loss', 'prec1', 'prec5', 'lr'])
train_batch_logger = Logger(
os.path.join(opt.result_path, 'train_batch.log'),
['epoch', 'batch', 'iter', 'loss', 'prec1', 'prec5', 'lr'])
if opt.nesterov:
dampening = 0
else:
dampening = opt.dampening
optimizer = optim.SGD(
parameters,
lr=opt.learning_rate,
momentum=opt.momentum,
dampening=dampening,
weight_decay=opt.weight_decay,
nesterov=opt.nesterov)
scheduler = lr_scheduler.ReduceLROnPlateau(
optimizer, 'min', patience=opt.lr_patience)
if not opt.no_val:
spatial_transform = Compose([
Scale(opt.sample_size),
CenterCrop(opt.sample_size),
ToTensor(opt.norm_value), norm_method
])
#temporal_transform = LoopPadding(opt.sample_duration)
temporal_transform = TemporalCenterCrop(opt.sample_duration, opt.downsample)
target_transform = ClassLabel()
validation_data = get_validation_set(
opt, spatial_transform, temporal_transform, target_transform)
val_loader = torch.utils.data.DataLoader(
validation_data,
batch_size=8,
shuffle=False,
num_workers=opt.n_threads,
pin_memory=True)
val_logger = Logger(
os.path.join(opt.result_path, opt.store_name + '_val.log'), ['epoch', 'loss', 'prec1', 'prec5'])
best_prec1 = 0
if opt.resume_path:
print('loading checkpoint {}'.format(opt.resume_path))
checkpoint = torch.load(opt.resume_path)
assert opt.arch == checkpoint['arch']
best_prec1 = checkpoint['best_prec1']
opt.begin_epoch = checkpoint['epoch']
model.load_state_dict(checkpoint['state_dict'])
print('run')
for i in range(opt.begin_epoch, opt.n_epochs + 1):
# for i in range(opt.begin_epoch, opt.begin_epoch + 10):
if not opt.no_train:
adjust_learning_rate(optimizer, i, opt)
train_epoch(i, train_loader, model, criterion, optimizer, opt,
train_logger, train_batch_logger)
state = {
'epoch': i,
'arch': opt.arch,
'state_dict': model.state_dict(),
'optimizer': optimizer.state_dict(),
'best_prec1': best_prec1
}
save_checkpoint(state, False, opt)
if not opt.no_val:
validation_loss, prec1 = val_epoch(i, val_loader, model, criterion, opt,
val_logger)
is_best = prec1 > best_prec1
best_prec1 = max(prec1, best_prec1)
state = {
'epoch': i,
'arch': opt.arch,
'state_dict': model.state_dict(),
'optimizer': optimizer.state_dict(),
'best_prec1': best_prec1
}
save_checkpoint(state, is_best, opt)
if opt.test:
spatial_transform = Compose([
Scale(int(opt.sample_size / opt.scale_in_test)),
CornerCrop(opt.sample_size, opt.crop_position_in_test),
ToTensor(opt.norm_value), norm_method
])
# temporal_transform = LoopPadding(opt.sample_duration, opt.downsample)
temporal_transform = TemporalRandomCrop(opt.sample_duration, opt.downsample)
target_transform = VideoID()
test_data = get_test_set(opt, spatial_transform, temporal_transform,
target_transform)
test_loader = torch.utils.data.DataLoader(
test_data,
batch_size=40,
shuffle=False,
num_workers=opt.n_threads,
pin_memory=True)
test.test(test_loader, model, opt, test_data.class_names)