pytorch实现线性回归实例

当使用PyTorch实现线性回归时，我们需要定义一个包含一个线性层的模型，并使用梯度下降优化算法来训练该模型。下面是一个简单的示例代码：

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

# 创建输入数据
x_train = np.array([[3.3], [4.4], [5.5], [6.71], [6.93], [4.168],
                    [9.779], [6.182], [7.59], [2.167], [7.042],
                    [10.791], [5.313], [7.997], [3.1]], dtype=np.float32)

y_train = np.array([[1.7], [2.76], [2.09], [3.19], [1.694], [1.573],
                    [3.366], [2.596], [2.53], [1.221], [2.827],
                    [3.465], [1.65], [2.904], [1.3]], dtype=np.float32)

# 转换为PyTorch的张量
x_train = torch.from_numpy(x_train)
y_train = torch.from_numpy(y_train)

# 定义线性回归模型
class LinearRegression(nn.Module):
    def __init__(self, input_dim, output_dim):
        super(LinearRegression, self).__init__()
        self.linear = nn.Linear(input_dim, output_dim)

    def forward(self, x):
        out = self.linear(x)
        return out

# 定义模型参数
input_dim = 1
output_dim = 1

# 实例化模型
model = LinearRegression(input_dim, output_dim)

# 定义损失函数和优化器
criterion = nn.MSELoss()
optimizer = optim.SGD(model.parameters(), lr=0.01)

# 训练模型
num_epochs = 2000
for epoch in range(num_epochs):
    # 前向传播
    outputs = model(x_train)
    loss = criterion(outputs, y_train)

    # 反向传播和优化
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

    # 每100个epoch打印一次损失
    if (epoch+1) % 100 == 0:
        print('Epoch [{}/{}], Loss: {:.4f}'.format(epoch+1, num_epochs, loss.item()))

# 打印训练后的模型参数
print('The trained parameters:')
for name, param in model.named_parameters():
    if param.requires_grad:
        print(name, param.data)

# 预测新数据
x_test = torch.tensor([[4.5], [7.8]])
predicted = model(x_test)
print('Predictions for new data:')
print(predicted.data)

 运行结果

------------------------------------
Epoch [100/2000], Loss: 0.1696
Epoch [200/2000], Loss: 0.1693
Epoch [300/2000], Loss: 0.1691
Epoch [400/2000], Loss: 0.1691
Epoch [500/2000], Loss: 0.1690
Epoch [600/2000], Loss: 0.1690
Epoch [700/2000], Loss: 0.1689
Epoch [800/2000], Loss: 0.1689
Epoch [900/2000], Loss: 0.1689
Epoch [1000/2000], Loss: 0.1689
Epoch [1100/2000], Loss: 0.1689
Epoch [1200/2000], Loss: 0.1689
Epoch [1300/2000], Loss: 0.1689
Epoch [1400/2000], Loss: 0.1689
Epoch [1500/2000], Loss: 0.1689
Epoch [1600/2000], Loss: 0.1689
Epoch [1700/2000], Loss: 0.1689
Epoch [1800/2000], Loss: 0.1689
Epoch [1900/2000], Loss: 0.1689
Epoch [2000/2000], Loss: 0.1689
------------------------------------
The trained parameters:
linear.weight tensor([[0.2599]])
linear.bias tensor([0.7482])
Predictions for new data:
tensor([[1.9178],
        [2.7755]])
------------------------------------

这个例子中，我们创建了一个包含一个线性层的简单的线性回归模型。我们使用均方误差（MSE）作为损失函数，并使用随机梯度下降（SGD）优化器来更新模型的参数。在训练过程中，我们通过反向传播计算梯度，并使用优化器更新参数。最后，我们使用训练好的模型进行新数据的预测。