PyTorch学习笔记（三）线性回归模型

# 导入相关库函数
import torch
import torchvision.transforms as transforms
import numpy as np
import torch.nn as nn
import matplotlib.pyplot as plt

# 超参数
input_size = 1
output_size = 1
num_epochs = 60
learning_rate = 0.001

# 数据集
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)

# 线性回归模型
model = nn.Linear(input_size,output_size)

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

# 训练模型
for epoch in range(num_epochs):
    # 将numpy数组转化为tensor
    inputs = torch.from_numpy(x_train)
    targets = torch.from_numpy(y_train)
    
    # 前向传播
    outputs = model(inputs)
    loss = criterion(outputs,targets)
    
    # 反向传播并优化
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    
    if (epoch+1) % 5 ==0:
        print('Epoch [{}/{}],Loss:{:.4f}'.format(epoch+1,num_epochs,loss.item()))

Epoch [5/60],Loss:36.0127
Epoch [10/60],Loss:14.7434
Epoch [15/60],Loss:6.1267
Epoch [20/60],Loss:2.6358
Epoch [25/60],Loss:1.2214
Epoch [30/60],Loss:0.6483
Epoch [35/60],Loss:0.4160
Epoch [40/60],Loss:0.3218
Epoch [45/60],Loss:0.2834
Epoch [50/60],Loss:0.2678
Epoch [55/60],Loss:0.2613
Epoch [60/60],Loss:0.2585

# 绘制结果
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 data')
plt.legend()
plt.show()

# 保存模型
torch.save(model.state_dict(),'model.ckpt')