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
|
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
import torchvision.transforms as transforms
import torchvision.datasets as datasets
import time
batch_size = 256
epochs = 300
lr = 1e-2
class AlexNet(nn.Module):
def __init__(self, num_classes=1000):
super(AlexNet, self).__init__()
self.features = nn.Sequential(
nn.Conv2d(3, 96, kernel_size=11, stride=4, padding=0),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Conv2d(96, 256, kernel_size=5, stride=1, padding=2),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Conv2d(256, 384, kernel_size=3, stride=1, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(384, 384, kernel_size=3, stride=1, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(384, 256, kernel_size=3, stride=1, padding=1),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
)
self.classifier = nn.Sequential(
nn.Dropout(),
nn.Linear(256 * 6 * 6, 4096),
nn.ReLU(inplace=True),
nn.Dropout(),
nn.Linear(4096, 4096),
nn.ReLU(inplace=True),
nn.Dropout(),
nn.Linear(4096, num_classes),
)
def forward(self, x):
x = self.features(x)
x = x.view(x.size(0), 256 * 6 * 6)
x = self.classifier(x)
return x
class AlexNet_v2(nn.Module):
...
def load_cifar_10_data(batch_size=128, shuffle=False):
data_dir = '/home/lab305/Documents/data/cifar_10/'
# data_dir = '/home/zj/zj/data/cifar_10/'
transform = transforms.Compose([
transforms.Resize((227, 227)),
transforms.ToTensor(),
transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))
])
train_data_set = datasets.CIFAR10(root=data_dir, train=True, download=True, transform=transform)
test_data_set = datasets.CIFAR10(root=data_dir, train=False, download=True, transform=transform)
train_loader = DataLoader(train_data_set, batch_size=batch_size, shuffle=shuffle, num_workers=8)
test_loader = DataLoader(test_data_set, batch_size=batch_size, shuffle=shuffle, num_workers=8)
return train_loader, test_loader
def compute_accuracy(loader, net, device):
total_accuracy = 0
num = 0
for item in loader:
data, labels = item
data = data.to(device)
labels = labels.to(device)
scores = net.forward(data)
predicted = torch.argmax(scores, dim=1)
total_accuracy += torch.mean((predicted == labels).float()).item()
num += 1
return total_accuracy / num
if __name__ == '__main__':
train_loader, test_loader = load_cifar_10_data(batch_size=batch_size, shuffle=True)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# device = torch.device("cpu")
# net = AlexNet(num_classes=10).to(device)
net = AlexNet_v2(num_classes=10).to(device)
criterion = nn.CrossEntropyLoss().to(device)
optimer = optim.SGD(net.parameters(), lr=lr, momentum=0.9, nesterov=True)
best_train_accuracy = 0.995
best_test_accuracy = 0
loss_list = []
train_list = []
for i in range(epochs):
num = 0
total_loss = 0
start = time.time()
net.train()
for j, item in enumerate(train_loader, 0):
data, labels = item
data = data.to(device)
labels = labels.to(device)
scores = net.forward(data)
loss = criterion.forward(scores, labels)
total_loss += loss.item()
optimer.zero_grad()
loss.backward()
optimer.step()
num += 1
end = time.time()
avg_loss = total_loss / num
loss_list.append(float('%.8f' % avg_loss))
print('epoch: %d time: %.2f loss: %.8f' % (i + 1, end - start, avg_loss))
if i % 20 == 19:
# 计算训练数据集检测精度
net.eval()
train_accuracy = compute_accuracy(train_loader, net, device)
train_list.append(float('%.4f' % train_accuracy))
if best_train_accuracy < train_accuracy:
best_train_accuracy = train_accuracy
test_accuracy = compute_accuracy(test_loader, net, device)
if best_test_accuracy < test_accuracy:
best_test_accuracy = test_accuracy
print('best train accuracy: %.2f %% best test accuracy: %.2f %%' % (
best_train_accuracy * 100, best_test_accuracy * 100))
print(loss_list)
print(train_list)
|
