简单的一维线性回归-pytorch

忘是亡心i 2024-02-19 15:06 65阅读 0赞

代码来自书籍《深度学习入门之pytorch》，书里有几个错误，修改好了

--------------------

>     import matplotlib.pyplot as plt
>     import torch
>     from torch import nn
>     from torch import optim
>     from torch.autograd import Variable
>     
>     import numpy as np
>     
>     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],
>                        [10.088],[5.33],[8.5],[4.2]],dtype=np.float32)
>     y_train = np.array([[1.7],[2.8],[2.3],[4.0],[6.3],[5.3],[6.2],[8.6],[9.9],[2.8],[6.3],
>                         [11.8],[8.5],[6.5],[3.8]],dtype=np.float32)
>     x_train = torch.from_numpy(x_train)
>     y_train = torch.from_numpy(y_train)
>     
>     #define a LinearRegression Class
>     class LinearRegression(nn.Module):
>         def __init__(self):
>             super(LinearRegression,self).__init__()
>             self.linear = nn.Linear(1,1)
>     
>         def forward(self, x):
>             out = self.linear(x)
>             return out
>     
>     
>     #create a model
>     if torch.cuda.is_available():
>         print('GPU1')
>         model = LinearRegression().cuda()
>     else:
>         print('CPU1')
>         model = LinearRegression()
>     
>     #define a optimizer
>     criterion = nn.MSELoss()
>     optimizer = optim.SGD(model.parameters(),lr=1e-3)
>     
>     #start to train model
>     num_epoch = 25000
>     for epoch in range(num_epoch):
>         if torch.cuda.is_available():
>             #print('GPU2')
>             inputs = Variable(x_train).cuda()
>             target = Variable(y_train).cuda()
>         else:
>             #print('CPU2')
>             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_epoch,loss.data[0]))
>     
>     model.eval()
>     if torch.cuda.is_available():
>         print('GPU3')
>         predict = model(Variable(x_train).cuda())
>         predict = predict.data.cpu().numpy()
>     else:
>         print('CPU3')
>         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='Predict Line')
>     plt.show()

运行结果：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3pzeDE3MTMzNjYyNDk_size_16_color_FFFFFF_t_70][]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3pzeDE3MTMzNjYyNDk_size_16_color_FFFFFF_t_70]: https://image.dandelioncloud.cn/pgy_files/images/2024/01/29/d95597c7c51546479081cfee53d25321.png