第一章基本操作-线性回归模型

Posted 2021-03-02 my-love-is-python

第一步:构造数据

import numpy as np
import os

x_values = [i for i in range(11)]
x_train = np.array(x_values, dtype=np.float32).reshape(-1, 1)

y_values = [i * 2 + 1 for i in x_values]
y_train = np.array(y_values, dtype=np.float32).reshape(-1, 1)

第二步: 使用class LinearRegressionModel 

class LinearRegressionModel(nn.Module):
    def __init__(self, input_dim, output_dim):
        super(LinearRegressionModel, self).__init__()
        self.linear = nn.Linear(input_dim, output_dim)
    def forward(self, x):
        out = self.linear(x)
        return out

第三步: 实例化模型，初始化epochs, 学习率，定义SGD优化函数，以及定义mse优化损失函数 

input_dim = 1
output_dim = 1

model = LinearRegressionModel(input_dim, output_dim)

epochs = 1000
learning_rate = 0.01
optimizer = torch.optim.SGD(model.parameters(), lr = learning_rate)
criterion = nn.MSELoss()

第四步: 如果模型存在就使用model.load_state_dict(torch.load("model.pkl")) 加载模型 参数，进行模型的参数优化，每50次,使用torch.save(model.state_dict)保存模型 

if os.path.exists("model.pkl"):
    model.load_state_dict(torch.load("model.pkl"))

for epoch in range(epochs):

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

    # 梯度每次清零
    optimizer.zero_grad()

    # 前向传播
    outputs = model(inputs)

    # 计算损失值
    loss = criterion(outputs, labels)

    #反向传播
    loss.backward()

    #更新权重参数
    optimizer.step()

    if epoch % 50 == 0:
        print("epoch:{},loss:{}".format(epoch, loss.item()))
        torch.save(model.state_dict(), "model.pkl")