# -- coding:utf-8 -- import torch import numpy as np from torch import nn, optim import matplotlib.pyplot as plt from torch.autograd import Variable # 設(shè)置字體為中文 plt.rcParams['font.sans-serif'] = ['SimHei'] plt.rcParams['axes.unicode_minus'] = False # 訓(xùn)練數(shù)據(jù) x_train = np.array([[3.3],[4.4],[5.5],[6.71],[6.93],[4.168],[9.779],[6.182],[7.59],[2.167],[7.042],[10.791],[5.313],[7.997],[3.1]],dtype=np.float32) y_train = np.array([[1.7],[2.76],[2.09],[3.19],[1.694],[1.573],[3.366],[2.596],[2.53],[1.221],[2.827],[3.465],[1.65],[2.904],[1.3]],dtype=np.float32) # 訓(xùn)練數(shù)據(jù)可視化 plt.scatter(x_train, y_train, marker='o', c='red') plt.title(label='一維線性回歸-原始數(shù)據(jù)分布展示') plt.show() # 把訓(xùn)練數(shù)據(jù)轉(zhuǎn)換為張量numpy->torch x_train = torch.from_numpy(x_train) y_train = torch.from_numpy(y_train)# 構(gòu)建線性模型 class LinearRegression(nn.Module):def __init__(self):super(LinearRegression, self).__init__()# 輸入和輸出的維度都是1self.linear = nn.Linear(1, 1)def forward(self, x):out = self.linear(x)return outif torch.cuda.is_available():model = LinearRegression().cuda() else:model = LinearRegression() # 損失函數(shù)：均方誤差 criterion = nn.MSELoss() # 采用隨機(jī)梯度下降 optimizer = optim.SGD(model.parameters(), lr=1e-3)num_epochs = 1000 # 訓(xùn)練總次數(shù) ctn = [] # 訓(xùn)練次數(shù) lo = [] # 損失值 for epoch in range(num_epochs):if torch.cuda.is_available():inputs = Variable(x_train).cuda()target = Variable(y_train).cuda()else:inputs = Variable(x_train)target = Variable(y_train)# 向前傳播out = model(inputs)loss = criterion(out, target)# 向后傳播optimizer.zero_grad() # 梯度清零loss.backward() # 向后傳播optimizer.step() # 更新參數(shù)# 統(tǒng)計(jì)每次對應(yīng)的損失值ctn.append(epoch+1)lo.append(loss.item())if (epoch + 1) % 20 == 0:print('Epoch[{}/{}], loss:{:.6f}'.format(epoch + 1, num_epochs, loss.item()))model.eval() if torch.cuda.is_available():predict = model(Variable(x_train).cuda())predict = predict.data.cpu().numpy() else: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='擬合的直線') plt.title(label='擬合的直線') plt.show() # 繪制訓(xùn)練次數(shù)與損失值之間的關(guān)系 plt.plot(ctn,lo) plt.title(label='訓(xùn)練次數(shù)與損失') plt.xlabel('訓(xùn)練次數(shù)') plt.ylabel('損失值') plt.show()

實(shí)驗(yàn)結(jié)果：

總結(jié)

以上是生活随笔為你收集整理的pytorch:一维线性回归(一)的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。