Step1准备数据输入
按需制作训练集
Step2 设计神经网络
注意forward()函数是override method，名字不能改
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 5 * 5, 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 * 5 * 5)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
net = Net()
Step3 定义损失函数和优化方法
import torch.optim as optim
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
Step4 训练网络
4.1 循环更新参数
- for epoch in range(times):
- 参数的梯度置零
- 前向传播获取神经网络的输出
- 比较输出与标签的差距并计算损失
- 损失反向传播
- 优化器更新参数
- 累计损失
for epoch in range(2): # loop over the dataset multiple times
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
# get the inputs; data is a list of [inputs, labels]
inputs, labels = data
# 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()
Step4 保存训练结果
torch.save(net.state_dict(), PATH)
Step5 恢复并评估模型
5.1恢复模型
net = Net()
net.load_state_dict(torch.load(PATH))
5.2 测试集前向传播得到输出
with torch.no_grad():
outputs = net(images)
