使用pytorch进行多变量线性回归

时间:2017-04-22 13:00:23

标签: pytorch

我正在使用Pytorch进行linear_regression 我用一个变量成功了。但是使用pytorch的multi_variable linear_regression 得到了一些错误。 我应该如何使用多变量进行线性回归?

  

TypeError Traceback(最近一次调用   最后)in()         9 optimizer.zero_grad()#gradient        10个输出=模型(输入)#output   ---> 11损失=标准(输出,目标)#loss功能        12 loss.backward()#backward propogation        13 optimizer.step()#1步优化(gradeint descent)

     

/anaconda/envs/tensorflow/lib/python3.6/site-packages/torch/nn/modules/module.py   在调用(自我,*输入,** kwargs)       204       205 def 调用(self,* input,** kwargs):    - > 206 result = self.forward(* input,** kwargs)       207 for hook in self._forward_hooks.values():       208 hook_result = hook(自我,输入,结果)

     

/anaconda/envs/tensorflow/lib/python3.6/site-packages/torch/nn/modules/loss.py   在前进(自我,输入,目标)        22 _assert_no_grad(目标)        23 backend_fn = getattr(self._backend,type(self)。 name )   ---> 24 return backend_fn(self.size_average)(输入,目标)        25        26

     

/anaconda/envs/tensorflow/lib/python3.6/site-packages/torch/nn/_functions/thnn/auto.py   在前进(自我,输入,目标)        39输出= input.new(1)        40 getattr(self._backend,update_output.name)(self._backend.library_state,input,target,   ---> 41输出,* self.additional_args)        42返回输出        43

     

TypeError:FloatMSECriterion_updateOutput收到无效   参数组合 - got(int,torch.FloatTensor,   torch.DoubleTensor,torch.FloatTensor,bool),但是预期的(int state,   torch.FloatTensor输入,torch.FloatTensor目标,torch.FloatTensor   输出,bool sizeAverage)

这是代码

#import
import torch
import torch.nn as nn
import numpy as np
import matplotlib.pyplot as plt
from torch.autograd import Variable

#input_size = 1
input_size = 3
output_size = 1
num_epochs = 300
learning_rate = 0.002

#Data set
#x_train = np.array([[1.564],[2.11],[3.3],[5.4]], dtype=np.float32)
x_train = np.array([[73.,80.,75.],[93.,88.,93.],[89.,91.,90.],[96.,98.,100.],[73.,63.,70.]],dtype=np.float32)
#y_train = np.array([[8.0],[19.0],[25.0],[34.45]], dtype= np.float32)
y_train = np.array([[152.],[185.],[180.],[196.],[142.]])
print('x_train:\n',x_train)
print('y_train:\n',y_train)

class LinearRegression(nn.Module):
    def __init__(self,input_size,output_size):
        super(LinearRegression,self).__init__()
        self.linear = nn.Linear(input_size,output_size)

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

model = LinearRegression(input_size,output_size)

#Lost and Optimizer
criterion = nn.MSELoss()
optimizer = torch.optim.SGD(model.parameters(),lr=learning_rate)

#train the Model
for epoch in range(num_epochs):
    #convert numpy array to torch Variable
    inputs = Variable(torch.from_numpy(x_train)) #convert numpy array to torch tensor
    #inputs = Variable(torch.Tensor(x_train))    
    targets = Variable(torch.from_numpy(y_train)) #convert numpy array to torch tensor

    #forward+ backward + optimize
    optimizer.zero_grad() #gradient
    outputs = model(inputs) #output
    loss = criterion(outputs,targets) #loss function
    loss.backward() #backward propogation
    optimizer.step() #1-step optimization(gradeint descent)

    if(epoch+1) %5 ==0:
        print('epoch [%d/%d], Loss: %.4f' % (epoch +1, num_epochs, loss.data[0]))
        predicted = model(Variable(torch.from_numpy(x_train))).data.numpy()
        plt.plot(x_train,y_train,'ro',label='Original Data')
        plt.plot(x_train,predicted,label='Fitted Line')
        plt.legend()
        plt.show()

1 个答案:

答案 0 :(得分:4)

您需要确保数据具有相同的类型。在这种情况下,x_train是32位浮点数,而y_train是Double。你必须使用:

y_train = np.array([[152.],[185.],[180.],[196.],[142.]],dtype=np.float32)