/
main.py
199 lines (170 loc) · 8.8 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
# coding=UTF-8
import argparse
import os
import torch
import torch.nn as nn
import torch.optim as optim
import torch.backends.cudnn as cudnn
from torch.optim import lr_scheduler
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
from dataset import CubDataset, CubTextDataset
from model import resnet50
from centerloss_real import CenterLoss
from train import *
from vidaite import *
def arg_parse():
parser = argparse.ArgumentParser(description='PyTorch HSE Deployment')
parser.add_argument('--gpu', default=1, type=int, required=False, help='GPU nums to use')
parser.add_argument('--workers', default=4, type=int, required=False, metavar='N',
help='number of data loading workers')
parser.add_argument('--epochs', default=200, type=int, required=False, metavar='N',
help='number of total epochs to run')
parser.add_argument('--snapshot', default='./epoch_143_0.3725.pkl', type=str, required=False, metavar='PATH',
help='path to latest checkpoint')
parser.add_argument('--batch_size', default=1, type=int, metavar='N', required=False, help='mini-batch size')
parser.add_argument('--data_path', default='/home/bjm/FGCrossNet_ACMMM2019-master/dataset', type=str, required=False, help='path to dataset')
parser.add_argument('--model_path', default='./model1/', type=str, required=False, help='path to model')
parser.add_argument('--crop_size', default=448, type=int, help='crop size')
parser.add_argument('--scale_size', default=512, type=int, help='the size of the rescale image')
parser.add_argument('--print_freq', default=500, type=int, metavar='N', help='print frequency')
parser.add_argument('--eval_epoch', default=1, type=int, help='every eval_epoch we will evaluate')
parser.add_argument('--eval_epoch_thershold', default=2, type=int, help='eval_epoch_thershold')
parser.add_argument('--loss_choose', default='r', type=str, required=False,
help='choose loss(c:centerloss, r:rankingloss)')
args = parser.parse_args()
return args
def print_args(args):
print("==========================================")
print("========== CONFIG =============")
print("==========================================")
for arg, content in args.__dict__.items():
print("{}:{}".format(arg, content))
print("\n")
def main():
args = arg_parse()
print_args(args)
print("==> Creating dataloader...")
data_dir = args.data_path
train_list = './list/image/train.txt'
train_set = get_train_set(data_dir, train_list, args)
train_list1 ='./list/video/train.txt'
train_set1 = get_train_set(data_dir, train_list1, args)
train_list2 = './list/audio/train.txt'
train_set2 = get_train_set(data_dir, train_list2, args)
train_list3 = './list/text/train.txt'
train_set3 = get_text_set(data_dir, train_list3, args, 'train')
test_list = './list/image/test.txt'
test_set = get_test_set(data_dir, test_list, args)
test_list1 = './list/video/test.txt'
test_set1 = get_test_set(data_dir, test_list1, args)
test_list2 = './list/audio/test.txt'
test_set2 = get_test_set(data_dir, test_list2, args)
test_list3 = './list/text/test.txt'
test_set3 = get_text_set(data_dir, test_list3, args, 'test')
test_loader=DataLoader(dataset=test_set, num_workers=args.workers, batch_size=args.batch_size, shuffle=False)
test_loader1=DataLoader(dataset=test_set1, num_workers=args.workers, batch_size=args.batch_size, shuffle=False)
test_loader2=DataLoader(dataset=test_set2, num_workers=args.workers, batch_size=args.batch_size, shuffle=False)
test_loader3=DataLoader(dataset=test_set3, num_workers=args.workers, batch_size=args.batch_size, shuffle=False)
print("==> Loading the network ...")
model = resnet50(num_classes=200)
center_loss = CenterLoss(200, 200, True)
if args.gpu is not None:
# model = nn.DataParallel(model, device_ids=range(args.gpu))
model = model.cuda()
cudnn.benchmark = True
if True: # os.path.isfile(args.snapshot):
print("==> loading checkpoint '{}'".format(args.snapshot))
checkpoint = torch.load(args.snapshot)
model_dict = model.state_dict()
restore_param = {k: v for k, v in checkpoint.items() if k in model_dict}
model_dict.update(restore_param)
model.load_state_dict(model_dict)
print("==> loaded checkpoint '{}'".format(args.snapshot))
else:
print("==> no checkpoint found at '{}'".format(args.snapshot))
# exit()
criterion = nn.CrossEntropyLoss()
# '''只训练指定层'''
#for i, v in center_loss.named_parameters():
# v.requires_grad = False
# for i, v in model.named_parameters():
# if i != 'embed.weight' and i != "conv01.weight" \
# and i != "conv01.bias" and i != "conv02.weight" \
# and i != "conv02.bias" and i != "conv0.weight" \
# and i != 'conv0.bias'and i != 'fc1.weight'and i != 'fc1.bias':
# v.requires_grad = False
params = list(model.parameters()) + list(center_loss.parameters())
optimizer = optim.SGD(filter(lambda p: p.requires_grad,params),
lr=0.001, momentum=0.9)
for name, param in model.named_parameters():
if param.requires_grad:
print(name)
for name, param in center_loss.named_parameters():
if param.requires_grad:
print(name)
scheduler = lr_scheduler.StepLR(optimizer, step_size=5, gamma=0.8)
savepath = args.model_path
if not os.path.exists(savepath):
os.makedirs(savepath)
if True:
print('-' * 20)
print("Video Acc:")
text_acc = validate(test_loader1, model, args,'v')
exit()
for epoch in range(args.epochs):
scheduler.step()
train_loader = DataLoader(dataset=train_set, num_workers=args.workers, batch_size=args.batch_size, shuffle=True)
train_loader1 = DataLoader(dataset=train_set1, num_workers=args.workers, batch_size=args.batch_size,
shuffle=True)
train_loader2 = DataLoader(dataset=train_set2, num_workers=args.workers, batch_size=args.batch_size,
shuffle=True)
train_loader3 = DataLoader(dataset=train_set3, num_workers=args.workers, batch_size=args.batch_size,
shuffle=True)
train(train_loader, train_loader1, train_loader2, train_loader3, args, model, criterion, center_loss, optimizer,
epoch, args.epochs)
if(epoch%1==0):
print("Image Acc:")
image1_acc = validate(test_loader, model, args, 'i')
print("Audio Acc:")
image_acc = validate(test_loader2, model, args, 'a')
print("Video Acc:")
text_acc = validate(test_loader1, model, args,'v')
print("Text Acc:")
image_acc = validate(test_loader3, model, args, 't')
save_model_path = savepath + 'epoch_' + str(epoch) + '_' + str(image_acc) + '.pkl'
torch.save(model.state_dict(), save_model_path)
def get_train_set(data_dir, train_list, args):
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
crop_size = args.crop_size
scale_size = args.scale_size
train_data_transform = transforms.Compose([
transforms.Resize((scale_size, scale_size)),
transforms.CenterCrop(crop_size),
transforms.ToTensor(),
normalize,
])
train_set = CubDataset(data_dir, train_list, train_data_transform)
#train_loader = DataLoader(dataset=train_set, num_workers=args.workers, batch_size=args.batch_size, shuffle=False)
return train_set
def get_test_set(data_dir, test_list, args):
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
crop_size = args.crop_size
scale_size = args.scale_size
test_data_transform = transforms.Compose([
transforms.Resize((scale_size, scale_size)),
transforms.CenterCrop(crop_size),
transforms.ToTensor(),
normalize,
])
test_set = CubDataset(data_dir, test_list, test_data_transform)
# test_loader = DataLoader(dataset=test_set, num_workers=args.workers, batch_size=args.batch_size, shuffle=False)
return test_set
def get_text_set(data_dir, test_list, args, split):
data_set = CubTextDataset(data_dir, test_list, split)
#data_loader = DataLoader(dataset=data_set, num_workers=args.workers, batch_size=args.batch_size, shuffle=False)
return data_set
if __name__ == "__main__":
main()