机器学习（3）Optimizer优化

最新推荐文章于 2025-01-04 10:15:16 发布

Superb_Day

最新推荐文章于 2025-01-04 10:15:16 发布

阅读量290

点赞数

分类专栏： pytorch机器学习文章标签：机器学习 python pytorch

本文链接：https://blog.csdn.net/qq_41754350/article/details/121118606

版权

import torch
import torch.utils.data as Data
import torch.nn.functional as F
import matplotlib.pyplot as plt

# torch.manual_seed(1)    # reproducible
#超参数：提前定义的参数
LR = 0.01
BATCH_SIZE = 32
EPOCH = 12

# fake dataset
x = torch.unsqueeze(torch.linspace(-1, 1, 1000), dim=1)
y = x.pow(2) + 0.1*torch.normal(torch.zeros(*x.size()))

# 看一眼 fake data 长啥样
#plt.scatter(x.numpy(), y.numpy())
#plt.show()

# 将数据放进去
torch_dataset = Data.TensorDataset(x, y)
loader = Data.DataLoader(dataset=torch_dataset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2,)


# 默认的network形式
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.hidden = torch.nn.Linear(1, 20)   # hidden layer
        self.predict = torch.nn.Linear(20, 1)   # output layer

    def forward(self, x):
        x = F.relu(self.hidden(x))      # activation function for hidden layer
        x