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
| # -*- coding: utf-8 -*-
"""
@author: zj
@file: tensorboard-fashion-mnist.py
@time: 2019-12-11
"""
import matplotlib.pyplot as plt
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
import torchvision.utils
learning_rate = 1e-3
moment = 0.9
epoches = 50
bsize = 256
# constant for classes
classes = ('T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle Boot')
def load_data(bsize):
# transforms
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5,), (0.5,))])
# datasets
trainset = torchvision.datasets.FashionMNIST('./data',
download=True,
train=True,
transform=transform)
testset = torchvision.datasets.FashionMNIST('./data',
download=True,
train=False,
transform=transform)
# dataloaders
trainloader = torch.utils.data.DataLoader(trainset, batch_size=bsize,
shuffle=True, num_workers=2)
testloader = torch.utils.data.DataLoader(testset, batch_size=bsize,
shuffle=False, num_workers=2)
return trainloader, testloader
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 4 * 4, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = x.view(-1, 16 * 4 * 4)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
def compute_accuracy(loader, net, device):
total_accu = 0.0
num = 0
for i, data in enumerate(loader, 0):
inputs, labels = data[0].to(device), data[1].to(device)
outputs = net.forward(inputs)
predicted = torch.argmax(outputs, dim=1)
total_accu += torch.mean((predicted == labels).float()).item()
num += 1
return total_accu / num
def draw(values, xlabel, ylabel, title, label):
fig = plt.figure()
plt.plot(list(range(len(values))), values, label=label)
plt.xlabel(xlabel)
plt.ylabel(ylabel)
plt.title(title)
plt.legend()
plt.show()
def train(trainloader, testloader, net, criterion, optimizer, device):
train_accu_list = list()
test_accu_list = list()
loss_list = list()
for epoch in range(epoches): # loop over the dataset multiple times
num = 0
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
# get the inputs; data is a list of [inputs, labels]
inputs, labels = data[0].to(device), data[1].to(device)
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
num += 1
# 每轮迭代完成后，记录损失值，计算训练集和测试集的检测精度
avg_loss = running_loss / num
print('[%d] loss: %.4f' % (epoch + 1, avg_loss))
loss_list.append(avg_loss)
train_accu = compute_accuracy(trainloader, net, device)
test_accu = compute_accuracy(testloader, net, device)
print('train: %.4f, test: %.4f' % (train_accu, test_accu))
train_accu_list.append(train_accu)
test_accu_list.append(test_accu)
print('Finished Training')
return train_accu_list, test_accu_list, loss_list
if __name__ == '__main__':
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)
net = Net().to(device)
criterion = nn.CrossEntropyLoss().to(device)
optimizer = optim.SGD(net.parameters(), lr=learning_rate, momentum=moment)
trainloader, testloader = load_data(bsize)
train_accu_list, test_accu_list, loss_list = train(trainloader, testloader, net, criterion, optimizer, device)
draw(train_accu_list, 'epoch', 'accuracy', 'train accuracy', 'fashion-mnist')
draw(test_accu_list, 'epoch', 'accuracy', 'test accuracy', 'fashion-mnist')
draw(loss_list, 'epoch', 'loss_value', 'loss', 'fashion-mnist')
|
