生成一个generative model的代码用于二分类

以下是一个简单的基于PyTorch的生成模型的二分类代码：

import torch
import torch.nn as nn
import torch.optim as optim
import numpy as np

class Generator(nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
        super(Generator, self).__init__()
        self.fc1 = nn.Linear(input_size, hidden_size)
        self.fc2 = nn.Linear(hidden_size, hidden_size)
        self.fc3 = nn.Linear(hidden_size, output_size)
        self.relu = nn.ReLU()
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        x = self.relu(self.fc1(x))
        x = self.relu(self.fc2(x))
        x = self.sigmoid(self.fc3(x))
        return x

input_size = 10
hidden_size = 50
output_size = 1

generator = Generator(input_size, hidden_size, output_size)

# Binary cross entropy loss function
loss_fn = nn.BCELoss()

# Optimizer
optimizer = optim.Adam(generator.parameters(), lr=0.01)

# Generate some random input data
X = torch.randn(1000, input_size)

# Generate some random output labels
Y = torch.FloatTensor(np.random.randint(2, size=(1000, 1)))

# Train the generator
for epoch in range(100):
    # Zero the gradients
    optimizer.zero_grad()

    # Generate output predictions
    Y_pred = generator(X)

    # Compute the loss
    loss = loss_fn(Y_pred, Y)

    # Backpropagate the loss
    loss.backward()

    # Update the weights
    optimizer.step()

    # Print the loss
    print('Epoch [{}/{}], Loss: {:.4f}'.format(epoch+1, 100, loss.item()))

在这个例子中，我们使用了一个具有三个线性层和ReLU和Sigmoid激活函数的生成器模型。我们使用二元交叉熵损失函数和Adam优化器来训练模型。我们随机生成了一些输入数据并使用随机标签来训练生成器。在每个时期，我们计算损失，反向传播损失并更新权重。