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
|
"""
@date: 2020/3/1 下午2:38
@file: svm.py
@author: zj
@description:
"""
import time
import copy
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
import torchvision.transforms as transforms
from torchvision.datasets import MNIST
def load_data():
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5,), (0.5,))
])
data_loaders = {}
data_sizes = {}
for name in ['train', 'val']:
data_set = MNIST('./data', download=True, transform=transform)
data_loader = DataLoader(data_set, shuffle=True, batch_size=128, num_workers=8)
data_loaders[name] = data_loader
data_sizes[name] = len(data_set)
return data_loaders, data_sizes
def hinge_loss(outputs, labels):
"""
折页损失计算
:param outputs: 大小为(N, num_classes)
:param labels: 大小为(N)
:return: 损失值
"""
num_labels = len(labels)
corrects = outputs[range(num_labels), labels].unsqueeze(0).T
margin = 1.0
margins = outputs - corrects + margin
loss = torch.sum(torch.max(margins, 1)[0]) / len(labels)
return loss
def train_model(data_loaders, model, criterion, optimizer, lr_scheduler, num_epochs=25, device=None):
since = time.time()
best_model_weights = copy.deepcopy(model.state_dict())
best_acc = 0.0
for epoch in range(num_epochs):
print('Epoch {}/{}'.format(epoch, num_epochs - 1))
print('-' * 10)
for phase in ['train', 'val']:
if phase == 'train':
model.train()
else:
model.eval()
running_loss = 0.0
running_corrects = 0
for inputs, labels in data_loaders[phase]:
inputs = inputs.reshape(-1, 28 * 28)
inputs = inputs.to(device)
labels = labels.to(device)
optimizer.zero_grad()
with torch.set_grad_enabled(phase == 'train'):
outputs = model(inputs)
_, preds = torch.max(outputs, 1)
loss = criterion(outputs, labels)
if phase == 'train':
loss.backward()
optimizer.step()
running_loss += loss.item() * inputs.size(0)
running_corrects += torch.sum(preds == labels.data)
if phase == 'train':
lr_scheduler.step()
epoch_loss = running_loss / data_sizes[phase]
epoch_acc = running_corrects.double() / data_sizes[phase]
print('{} Loss: {:.4f} Acc: {:.4f}'.format(
phase, epoch_loss, epoch_acc))
if phase == 'val' and epoch_acc > best_acc:
best_acc = epoch_acc
best_model_weights = copy.deepcopy(model.state_dict())
print()
time_elapsed = time.time() - since
print('Training complete in {:.0f}m {:.0f}s'.format(
time_elapsed // 60, time_elapsed % 60))
print('Best val Acc: {:4f}'.format(best_acc))
model.load_state_dict(best_model_weights)
return model
if __name__ == '__main__':
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
data_loaders, data_sizes = load_data()
model = nn.Linear(28 * 28, 10).to(device)
criterion = hinge_loss
optimizer = optim.SGD(model.parameters(), lr=1e-3, momentum=0.9)
lr_schduler = optim.lr_scheduler.StepLR(optimizer, step_size=7, gamma=0.1)
train_model(data_loaders, model, criterion, optimizer, lr_schduler, num_epochs=25, device=device)
|