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
| """
This code is supported by the website: https://www.guanjihuan.com
The newest version of this code is on the web page: https://www.guanjihuan.com/archives/43720
"""
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, TensorDataset
from torchvision import datasets, transforms
transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.5,), (0.5,))])
train_dataset = datasets.MNIST(root='./data', train=True, download=True, transform=transform)
test_dataset = datasets.MNIST(root='./data', train=False, download=True, transform=transform)
def train(model, train_loader, criterion, optimizer, num_epochs=5):
for epoch in range(num_epochs):
model.train()
running_loss = 0.0
correct = 0
total = 0
for images, labels in train_loader:
optimizer.zero_grad()
outputs = model(images)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
_, predicted = torch.max(outputs, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
avg_loss = running_loss / len(train_loader)
accuracy = 100 * correct / total
print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {avg_loss:.4f}, Accuracy: {accuracy:.2f}%')
def test(model, test_loader):
model.eval()
correct = 0
total = 0
with torch.no_grad():
for images, labels in test_loader:
outputs = model(images)
_, predicted = torch.max(outputs, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
accuracy = 100 * correct / total
print(f'Test Accuracy: {accuracy:.2f}%')
def train_and_test(model, train_loader, test_loader):
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)
train(model, train_loader, criterion, optimizer, num_epochs=10)
test(model, test_loader)
def flatten_data(data_loader):
images_array = []
labels_array = []
for images, labels in data_loader:
images = torch.flatten(images, start_dim=1)
images_array.append(images)
labels_array.append(labels)
images_array = torch.cat(images_array, dim=0)
labels_array = torch.cat(labels_array, dim=0)
dataset_new = TensorDataset(images_array, labels_array)
loader_new = DataLoader(dataset_new, batch_size=64, shuffle=True)
return loader_new
train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=64, shuffle=False)
train_loader_new = flatten_data(train_loader)
test_loader_new = flatten_data(test_loader)
import guan
hidden_size = 64
print('---全连接神经网络模型（包含一个隐藏层）---')
model = guan.fully_connected_neural_network_with_one_hidden_layer(input_size=28*28, hidden_size=hidden_size, output_size=10, activation='relu')
train_and_test(model, train_loader_new, test_loader_new)
print('---全连接神经网络模型（包含两个隐藏层）---')
model = guan.fully_connected_neural_network_with_two_hidden_layers(input_size=28*28, hidden_size_1=hidden_size, hidden_size_2=hidden_size, output_size=10, activation_1='relu', activation_2='relu')
train_and_test(model, train_loader_new, test_loader_new)
print('---全连接神经网络模型（包含三个隐藏层）---')
model = guan.fully_connected_neural_network_with_three_hidden_layers(input_size=28*28, hidden_size_1=hidden_size, hidden_size_2=hidden_size, hidden_size_3=hidden_size, output_size=10, activation_1='relu', activation_2='relu', activation_3='relu')
train_and_test(model, train_loader_new, test_loader_new)
print('---卷积神经网络模型（包含两个卷积层和两个全连接层）---')
model = guan.convolutional_neural_network_with_two_convolutional_layers_and_two_fully_connected_layers(in_channels=1, out_channels_1=32, out_channels_2=64, kernel_size_1=3, kernel_size_2=3, stride_1=1, stride_2=1, padding_1=1, padding_2=1, pooling=1, pooling_kernel_size=2, pooling_stride=2, input_size=7*7*64, hidden_size_1=hidden_size, hidden_size_2=hidden_size, output_size=10)
train_and_test(model, train_loader, test_loader)
|
