|
|
import torch
|
|
|
import torch.nn as nn
|
|
|
import torch.optim as optim
|
|
|
import torch.nn.functional as F
|
|
|
import torchvision
|
|
|
import matplotlib.pyplot as plt
|
|
|
import numpy as np
|
|
|
|
|
|
input_size = 28
|
|
|
num_classes = 10
|
|
|
num_epochs = 40
|
|
|
batch_size = 64
|
|
|
|
|
|
# 确保 CUDA 可用并且使用它
|
|
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
|
|
|
|
|
train_dataset = torchvision.datasets.MNIST(
|
|
|
root='./data', train=True, transform=torchvision.transforms.ToTensor(), download=True
|
|
|
)
|
|
|
test_dataset = torchvision.datasets.MNIST(root='./data', train=False, transform=torchvision.transforms.ToTensor())
|
|
|
|
|
|
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
|
|
|
batch_size=batch_size,
|
|
|
shuffle=True)
|
|
|
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
|
|
|
batch_size=batch_size,
|
|
|
shuffle=True)
|
|
|
|
|
|
#定义了一个CNN类作为神经网络模型
|
|
|
# in_channels：输入数据的通道数。在第一层卷积中，输入的MNIST图像是灰度图像，因此 in_channels=1。
|
|
|
# out_channels：输出的特征图通道数，即卷积核的数量。每个卷积核生成一个特征图。
|
|
|
# kernel_size：卷积核的大小。例如，kernel_size=5 表示卷积核大小为5x5。
|
|
|
# stride：卷积核的步幅。在代码中设置为1，表示卷积核每次移动1个像素。
|
|
|
# padding：填充的像素数。在代码中设置为2，表示在输入数据周围填充2个像素。
|
|
|
class CNN(nn.Module):
|
|
|
def __init__(self):
|
|
|
super(CNN, self).__init__()
|
|
|
self.conv1 = nn.Sequential(
|
|
|
nn.Conv2d(1, 16, 5, 1, 2),
|
|
|
nn.ReLU(),
|
|
|
nn.MaxPool2d(2)
|
|
|
)
|
|
|
self.conv2 = nn.Sequential(
|
|
|
nn.Conv2d(16, 32, 5, 1, 2),
|
|
|
nn.ReLU(),
|
|
|
nn.MaxPool2d(2)
|
|
|
)
|
|
|
self.conv3 = nn.Sequential(
|
|
|
nn.Conv2d(32, 64, 5, 1, 2),
|
|
|
nn.ReLU(),
|
|
|
nn.MaxPool2d(2)
|
|
|
)
|
|
|
self.conv4 = nn.Sequential(
|
|
|
nn.Conv2d(64, 32, 5, 1, 2),
|
|
|
nn.ReLU(),
|
|
|
nn.MaxPool2d(2)
|
|
|
)
|
|
|
self.out = nn.Linear(32, num_classes) # 确保输出类别数正确
|
|
|
|
|
|
def forward(self, x):
|
|
|
x = self.conv1(x).to(device) # 将数据迁移到GPU
|
|
|
x = self.conv2(x).to(device)
|
|
|
x=self.conv3(x).to(device)
|
|
|
x = self.conv4(x).to(device)
|
|
|
x = x.view(x.size(0), -1).to(device)
|
|
|
x = self.out(x).to(device)
|
|
|
return x
|
|
|
|
|
|
def accuracy(prediction, label):
|
|
|
pred = torch.max(prediction.data, 1)[1]
|
|
|
rights = pred.eq(label.data.view_as(pred)).sum()
|
|
|
return rights, len(label)
|
|
|
|
|
|
net = CNN().to(device) # 将模型迁移到GPU
|
|
|
criterion = nn.CrossEntropyLoss().to(device) # 将损失函数迁移到GPU
|
|
|
optimizer = optim.Adam(net.parameters(), lr=0.001)
|
|
|
|
|
|
tr = []
|
|
|
for epoch in range(40):
|
|
|
train_rights = []
|
|
|
for batch_id, (data, target) in enumerate(train_loader):
|
|
|
data, target = data.to(device), target.to(device) # 将数据迁移到GPU
|
|
|
optimizer.zero_grad()
|
|
|
output = net(data)
|
|
|
loss = criterion(output, target)
|
|
|
loss.backward()
|
|
|
optimizer.step()
|
|
|
right = accuracy(output, target)
|
|
|
train_rights.append(right)
|
|
|
tr.append(loss)
|
|
|
if batch_id % 100 == 0:
|
|
|
val_right = []
|
|
|
for (data, target) in test_loader:
|
|
|
data, target = data.to(device), target.to(device) # 将数据迁移到GPU
|
|
|
output = net(data)
|
|
|
right = accuracy(output, target)
|
|
|
val_right.append(right)
|
|
|
train_r = (sum(t[0] for t in train_rights), sum(t[1] for t in train_rights))
|
|
|
val_r = (sum(t[0] for t in val_right), sum(t[1] for t in val_right))
|
|
|
print("train_acc {}, test_acc {}".format(train_r[0] / train_r[1], val_r[0] / val_r[1]))
|
|
|
|
|
|
# 注意，绘图时不需要将数据迁移到GPU
|
|
|
plt.plot(list(range(len([tensor.detach().cpu().numpy() for tensor in tr]))), [tensor.detach().cpu().numpy() for tensor in tr])
|
|
|
plt.show()
|
|
|
torch.save(net.state_dict(), 'model.pth')
|
