使用 PyTorch 构建多层神经网络进行 HIV 状态预测

import torch
import torch.nn as nn
import torch.optim as optim
import pandas as pd

# 读取Excel表格
data = pd.read_excel('C:\Users\lenovo\Desktop\HIV\DNN神经网络测试\data1.xlsx')
x = data.iloc[:, 1:].values  # 取除第一列以外的所有列，即基因的表达量
y = data.iloc[:, 0].values  # 取第一列，即患者状态标志state

# 定义第一个模型，输出为8分类
class Model1(nn.Module):
    def __init__(self):
        super(Model1, self).__init__()
        self.fc1 = nn.Linear(16, 128)
        self.fc2 = nn.Linear(128, 64)
        self.fc3 = nn.Linear(64, 32)
        self.fc4 = nn.Linear(32, 16)
        self.fc5 = nn.Linear(16, 8)
        self.dropout = nn.Dropout(0.2)

    def forward(self, x):
        x = nn.functional.relu(self.fc1(x))
        x = self.dropout(x)
        x = nn.functional.relu(self.fc2(x))
        x = self.dropout(x)
        x = nn.functional.relu(self.fc3(x))
        x = self.dropout(x)
        x = nn.functional.relu(self.fc4(x))
        x = self.dropout(x)
        x = self.fc5(x)
        return x

# 定义第二个模型，输入为第一个模型的8分类输出，输出为4分类
class Model2(nn.Module):
    def __init__(self):
        super(Model2, self).__init__()
        self.fc1 = nn.Linear(8, 16)
        self.fc2 = nn.Linear(16, 8)
        self.fc3 = nn.Linear(8, 4)
        self.dropout = nn.Dropout(0.2)

    def forward(self, x):
        x = nn.functional.relu(self.fc1(x))
        x = self.dropout(x)
        x = nn.functional.relu(self.fc2(x))
        x = self.dropout(x)
        x = self.fc3(x)
        return x

# 定义第三个模型，第三个模型为二分类模型，输入为第二个模型的4分类输出
class Model3(nn.Module):
    def __init__(self):
        super(Model3, self).__init__()
        self.fc1 = nn.Linear(4, 8)
        self.fc2 = nn.Linear(8, 1)
        self.dropout = nn.Dropout(0.2)

    def forward(self, x):
        x = nn.functional.relu(self.fc1(x))
        x = self.dropout(x)
        x = torch.sigmoid(self.fc2(x))
        return x

# 将数据转换为张量
x = torch.tensor(x).float()
y = torch.tensor(y).float().squeeze(1) # 修改标签y的维度

# 定义损失函数和优化器
criterion1 = nn.CrossEntropyLoss()
criterion2 = nn.CrossEntropyLoss()
criterion3 = nn.BCELoss()
model1 = Model1()
optimizer1 = optim.Adam(model1.parameters(), lr=0.001)

# 训练第一个模型
for epoch in range(100):
    optimizer1.zero_grad()
    output1 = model1(x)
    loss1 = criterion1(output1, y.long())
    loss1.backward()
    optimizer1.step()
    acc1 = (output1.argmax(dim=1) == y).float().mean()
    print('Epoch [{}/{}], Loss: {:.4f}, Accuracy: {:.4f}'.format(epoch+1, 100, loss1.item(), acc1.item()))

# 训练第二个模型
model2 = Model2()
output1 = model1(x)
output2 = model2(output1)
optimizer2 = optim.Adam(model2.parameters(), lr=0.001)
for epoch in range(100):
    optimizer2.zero_grad()
    loss2 = criterion2(output2, output1.argmax(dim=1).long())
    loss2.backward()
    optimizer2.step()
    acc2 = (output2.argmax(dim=1) == output1.argmax(dim=1)).float().mean()
    print('Epoch [{}/{}], Loss: {:.4f}, Accuracy: {:.4f}'.format(epoch+1, 100, loss2.item(), acc2.item()))

# 训练第三个模型
model3 = Model3()
output3 = model3(output2)
optimizer3 = optim.Adam(model3.parameters(), lr=0.001)
for epoch in range(100):
    optimizer3.zero_grad()
    loss3 = criterion3(output3, y)
    loss3.backward()
    optimizer3.step()
    acc3 = ((output3 > 0.5) == y).float().mean()
    print('Epoch [{}/{}], Loss: {:.4f}, Accuracy: {:.4f}'.format(epoch+1, 100, loss3.item(), acc3.item()))

上述代码运行至：loss1 = criterion1(output1, y.long()) 出现了错误：loss1 = criterion1(output1, y.long()) 为什么，具体怎么解决内容：

这个错误可能是因为标签 y 的维度不正确导致的。可以尝试使用 y.squeeze(1) 将标签 y 的维度从二维张量（n,1）变为一维张量（n），然后再传入损失函数中。修改代码如下：

# 将数据转换为张量
x = torch.tensor(x).float()
y = torch.tensor(y).float().squeeze(1) # 修改标签y的维度

# 定义损失函数和优化器
criterion1 = nn.CrossEntropyLoss()
criterion2 = nn.CrossEntropyLoss()
criterion3 = nn.BCELoss()
model1 = Model1()
optimizer1 = optim.Adam(model1.parameters(), lr=0.001)

# 训练第一个模型
for epoch in range(100):
    optimizer1.zero_grad()
    output1 = model1(x)
    loss1 = criterion1(output1, y.long())
    loss1.backward()
    optimizer1.step()
    acc1 = (output1.argmax(dim=1) == y).float().mean()
    print('Epoch [{}/{}], Loss: {:.4f}, Accuracy: {:.4f}'.format(epoch+1, 100, loss1.item(), acc1.item()))