pytorch搭建Regression

入门神经网络搭建

import torch
import matplotlib.pyplot as plt
from torch.autograd import Variable
import torch.nn.functional as F

x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1)
y = x.pow(2) + 0.2 * torch.rand(x.size())

X, Y = Variable(x), Variable(y)

plt.scatter(X.data.numpy(), Y.data.numpy())
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-wMxlF2h6-1644318579449)(img/1.png)]

构造噪声的散点图

构建神经网络

class Net(torch.nn.Module):
    def __init__(self, n_feature, n_hidden, n_output):
        # 特征，隐藏层，输出层
        super(Net, self).__init__()
        self.hidden = torch.nn.Linear(n_feature, n_hidden)
        self.predict = torch.nn.Linear(n_hidden, n_output)


    def forward(self, x): # 前向传递的过程
        x = F.relu(self.hidden(x))
        x = self.predict(x) # 预测的时候不改变取值范围
        return x


net = Net(1, 10, 1)
print(net)

out

Net(
  (hidden): Linear(in_features=1, out_features=10, bias=True)
  (predict): Linear(in_features=10, out_features=1, bias=True)
)

优化器进行优化

plt.ion() # 实时打印
plt.show()

# 优化神经网络

optimizer = torch.optim.SGD(net.parameters(), lr=0.5)
loss_func = torch.nn.MSELoss()

for i in range(100): # 训练一百步
    prediction = net(x) #

    loss = loss_func(prediction, y) # 误差

    optimizer.zero_grad() # 先梯度降为0
    loss.backward() # 反向传递
    optimizer.step() # 优化梯度

    if i % 5 == 0:
        plt.cla()
        plt.scatter(x.data.numpy(), y.data.numpy())
        plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)
        plt.text(0.5, 0, 'LOSS=%.4f' % loss.item(), fontdict={'size': 20, 'color': 'red'})
        plt.pause(0.1)

plt.ioff()
plt.show()

out

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-a9WHfeK6-1644318579451)(img/2.png)]

.pause(0.1)

plt.ioff()
plt.show()

**out**

[外链图片转存中...(img-a9WHfeK6-1644318579451)]