基于PyTorch实现一元线性回归模型

import torch
from torch.autograd import Variable
import matplotlib.pyplot as plt
import numpy as np
import torch.nn as nn
import torch.optim as optim

# step1:制造数据集
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)

x_train = torch.from_numpy(x_train)
y_train = torch.from_numpy(y_train)

# step2:建立线性回归模型这里的nn.Linear表示的是y=wx+b,input_size表示的是自变量x的尺寸，
# 是一维的，output_size表示的是因变量y的尺寸，也是一维
class LinearRegression(nn.Module):
    def __init__(self):
        super(LinearRegression, self).__init__()
        self.linear = nn.Linear(1, 1)

    def forward(self, x):
        out = self.linear(x)
        return out
# 实例化LinearRegression
model = LinearRegression()
# step4:定义损失函数
criterion = nn.MSELoss()
# step5:定义一个优化函数
optimizer = optim.SGD(model.parameters(), lr=0.01)
# step6 训练模型
"""
    首先要确定迭代的次数，这里设计的是1000次，先进行前向传播计算损失，然后进行反向传播计算梯度。
    每次计算梯度前都要将梯度归0，不然梯度会累加到一起造成结果不收敛。为了便于查看结果，每隔一段
    时间输出一次当前迭代的次数和损失
"""
num_epochs = 1000
for epoch in range(num_epochs):
    inputs = Variable(x_train)
    target = Variable(y_train)

    # 前向传播
    out = model(inputs)
    loss = criterion(out, target)
    # 后向传播
    optimizer.zero_grad()
    loss.backward()
    # 优化
    optimizer.step()
    # 更新参数
    if (epoch+1) % 20 == 0:
        print('Epoch[{}/{}],loss:{:.6f}'.format(epoch+1, num_epochs, loss.item()))
# step7 模型测试
if __name__ == '__main__':
    model.eval()
    predict = model(Variable(x_train))
    predict = predict.data.numpy()
    plt.plot(x_train.numpy(), y_train.numpy(), 'ro', label='Original data')
    plt.plot(x_train.numpy(), predict, label='Fitting Line')
    plt.show()