2021-03-03

pytorch入门

import torch.optim
import torch.nn

import torch

x_data = torch.Tensor([[1.0], [2.0], [3.0]])
y_data = torch.Tensor([[2.0], [4.0], [6.0]])


class LinearModel(torch.nn.Module):
    def __init__(self):
        super(LinearModel, self).__init__()
        self.linear = torch.nn.Linear(1, 1)

    def forward(self, x):
        y_pred = self.linear(x)
        return y_pred
    
"""首先实用类定义一个对象（网络结构+前向传播）
实例化对象，生成模型。实例化损失函数和优化器
开始训练for迭代，几个步骤：
                    1.输入数据、前向传播
                    2.计算损失函数
                    3.优化器梯度归零
                    4.反向传播
                    5.更新参数
"""
                        

model = LinearModel()  # 实例化
mse_loss = torch.nn.MSELoss(size_average=False)  # 实例化损失函数
optimizer = torch.optim.Adam(model.parameters(), lr=0.05,)  # 实例化优化器

for epoch in range(1000):
    # 开始训练，前向传播，计算损失函数，优化器归零，反正传播，优化器更新参数
    y_pred = model(x_data)
    loss = mse_loss(y_pred, y_data)
    print(epoch, loss)
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

print("w", model.linear.weight.item())
print("b", model.linear.bias.item())
x_test = torch.Tensor([[4.0]])
y_test = model(x_test)
print("y_pred",y_test.data)