【PyTorch】线性回归/Linear Regression

1. 模型说明

用PyTorch实现线性回归比较简单，主要是调用内置函数
nn.Linear(input_size, output_size)，然后使用自动微分和随机梯度下降SGD来更新模型参数。

2. 相关代码

具体代码实现如下：

import torch
import torch.nn as nn
import numpy as np
import matplotlib.pyplot as plt # plot tool

# Hyper -parameters
input_size = 1
output_size = 1
num_epochs = 60 # train time
learning_rate = 0.001

# Toy dataset
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)

# Linear regression model
model = nn.Linear(input_size, output_size) 

# Loss and optimizer
criterion = nn.MSELoss()
optimizer = torch.optim.SGD(
    model.parameters(),
    lr = learning_rate
)

# Train the model
for epoch in range(num_epochs):
    # Convert numpy arrays to torch tensors
    inputs = torch.from_numpy(x_train)
    targets = torch.from_numpy(y_train)

    # Forward pass
    outputs = model(inputs)
    loss = criterion(outputs, targets)

    # Backward and optimize
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

    if (epoch+1)%5 == 0:
        print ('Epoch [{}/{}], Loss: {:.4f}'.format(epoch+1, num_epochs, loss.item()))

# Plot the graph
predicted = model(torch.from_numpy(x_train)).detach().numpy()
plt.plot(x_train, y_train, 'ro', label='Original data')
plt.plot(x_train, predicted, label='Fitted line')
plt.legend()
plt.show()

# Save the model checkpoint
torch.save(model.state_dict()), 'model.ckpt'

3. 输出结果

每5 epochs输出一次Loss，结果如下：

Epoch [5/60], Loss: 9.8310
Epoch [10/60], Loss: 4.1846
Epoch [15/60], Loss: 1.8968
Epoch [20/60], Loss: 0.9698
Epoch [25/60], Loss: 0.5940
Epoch [30/60], Loss: 0.4414
Epoch [35/60], Loss: 0.3794
Epoch [40/60], Loss: 0.3540
Epoch [45/60], Loss: 0.3435
Epoch [50/60], Loss: 0.3389
Epoch [55/60], Loss: 0.3369
Epoch [60/60], Loss: 0.3358

这里还用matplotlib.pyplot进行绘图，得到数据点和拟合曲线的对照情况。