一剑霜寒十四州

最新推荐文章于 2025-04-30 15:03:34 发布

m0_61634665

最新推荐文章于 2025-04-30 15:03:34 发布

阅读量73

点赞数

文章标签：深度学习人工智能机器学习神经网络

本文链接：https://blog.csdn.net/m0_61634665/article/details/129658177

版权

该代码段展示了一个使用PyTorch构建的神经网络模型，包括两个全连接层（fc1,fc2,fc3），使用ReLU激活函数和LogSoftmax损失函数。模型在SGD优化器下进行训练，打印训练过程中的损失，并在测试集上计算平均损失和准确性。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import torch.nn as nn
import torch.nn.functional as F

class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.fc1 = nn.Linear(28 * 28, 200)
self.fc2 = nn.Linear(200, 200)
self.fc3 = nn.Linear(200, 10)

def forward(self, x):
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return F.log_softmax(x)
net = Net()
print(net)

Net (
(fc1): Linear (784 -> 200)
(fc2): Linear (200 -> 200)
(fc3): Linear (200 -> 10)
)

optimizer = optim.SGD(net.parameters(), lr=learning_rate, momentum=0.9)
criterion = nn.NLLLoss()

# 运行主训练循环
for epoch in range(epochs):
for batch_idx, (data, target) in enumerate(train_loader):
data, target = Variable(data), Variable(target)
# 将数据大小从 (batch_size, 1, 28, 28) 变为 (batch_size, 28*28)
data = data.view(-1, 28*28)
optimizer.zero_grad()
net_out = net(data)
loss = criterion(net_out, target)
loss.backward()
optimizer.step()
if batch_idx % log_interval == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.data[0]))
loss.backward()
optimizer.step()

if batch_idx % log_interval == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.data[0]))
# 运行测试循环
test_loss = 0
correct = 0
for data, target in test_loader:
data, target = Variable(data, volatile=True), Variable(target)
data = data.view(-1, 28 * 28)
net_out = net(data)
# 对批处理损失求和
test_loss += criterion(net_out, target).data[0]
pred = net_out.data.max(1)[1] # 得到有最大log概率的下标
correct += pred.eq(target.data).sum()

test_loss /= len(test_loader.dataset)
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))
test_loss /= len(test_loader.dataset)
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))