使用pytorch進行線性回歸

x,y
3.3,1.7
4.4,2.76
5.5,2.09
6.71,3.19
6.93,1.694
4.168,1.573
9.779,3.366
6.182,2.596
7.59,2.53
2.167,1.221
7.042,2.827
10.791,3.465
5.313,1.65
7.997,2.904
3.1,1.3

以上是欲擬合數據

import torch
from torch import nn, optim
from torch.autograd import Variable
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

d = pd.read_csv("data.csv")
x_train = np.array(d.x[:],dtype=np.float32).reshape(15,1)

print(x_train)
y_train=np.array(d.y[:],dtype=np.float32).reshape(15,1)
print(y_train)

x_train = torch.from_numpy(x_train)

y_train = torch.from_numpy(y_train)


# Linear Regression Model
class LinearRegression(nn.Module):
    def __init__(self):
        super(LinearRegression, self).__init__()
        self.linear = nn.Linear(1, 1)  # input and output is 1 dimension

    def forward(self, x):
        out = self.linear(x)
        return out


model = LinearRegression()
# 定義loss和優化函數
criterion = nn.MSELoss()
optimizer = optim.SGD(model.parameters(), lr=1e-4)

# 開始訓練
num_epochs = 1000
for epoch in range(num_epochs):
    inputs = Variable(x_train)
    target = Variable(y_train)

    # forward
    out = model(inputs)
    loss = criterion(out, target)
    # backward
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

    if (epoch+1) % 20 == 0:
        print('Epoch[{}/{}], loss: {:.6f}'
              .format(epoch+1, num_epochs, loss.data[0]))

model.eval()
predict = model(Variable(x_train))
predict = predict.data.numpy()
plt.plot(x_train.numpy(), y_train.numpy(), 'ro', label='Original data')
plt.plot(x_train.numpy(), predict, label='Fitting Line')
# 顯示圖例
plt.legend()
plt.show()

# 保存模型
torch.save(model.state_dict(), './linear.pth')