简单线性回归实现

import torch
import numpy as np
import torch.nn as nn
import matplotlib.pyplot as plt


# 生成数据
sample_nums = 100
mean_value = 1.7
bias = 1
n_data = torch.ones(sample_nums, 2)
x0 = torch.normal(mean_value*n_data, 1) + bias
y0 = torch.zeros(sample_nums)
x1 = torch.normal(-mean_value*n_data, 1) + bias
y1 = torch.ones(sample_nums)
train_x = torch.cat((x0, x1), 0)
train_y = torch.cat((y0, y1), 0)


# 选择模型
class LR(nn.Module):
    def __init__(self):
        super(LR, self).__init__()
        self.features = nn.Linear(2, 1)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        x = self.features(x)
        x = self.sigmoid(x)
        return x


lr_net = LR()
loss_fn = nn.BCELoss()
lr = 0.01
optimizer = torch.optim.SGD(lr_net.parameters(), lr=lr, momentum=0.9)

# 模型训练
for iteration in range(1000):
    y_pred = lr_net(train_x)
    loss = loss_fn(y_pred.squeeze(), train_y)
    loss.backward()
    optimizer.step()

    if iteration % 10 == 0:

        mask = y_pred.ge(0.5).float().squeeze()
        correct = (mask == train_y).sum()
        acc = correct.item()/train_y.size(0)
        print(iteration)

        plt.scatter(x0.data.numpy()[:, 0], x0.data.numpy()[:, 1], c='r', label='class0')
        plt.scatter(x1.data.numpy()[:, 0], x1.data.numpy()[:, 1], c='b', label='class1')

        w0, w1 = lr_net.features.weight[0]
        w0, w1 = float(w0.item()), float(w1.item())
        plt_b = float(lr_net.features.bias[0].item())
        plt_x = np.arange(-6, 6, 0.1)
        plt_y = (-w0 * plt_x - plt_b) / w1
        plt.plot(plt_x, plt_y)

        plt.text(-5, 5, 'Loss=%.4f' % loss.data.numpy(), fontdict={'size': 20, 'color': 'red'})

        plt.xlim(-5, 7)
        plt.ylim(-5, 7)
        plt.show(block=False)
        plt.pause(0.15)
        plt.clf()

        if loss.data.numpy() < 0.0001:
            print("success")
            break