PyTorch之线性回归-Toy模板网

这篇具有很好参考价值的文章主要介绍了PyTorch之线性回归。希望对大家有所帮助。如果存在错误或未考虑完全的地方，请大家不吝赐教，您也可以点击"举报违法"按钮提交疑问。

PyTorch之线性回归

第1关：初始化参数

import torch
import torchvision.datasets as dsets
import torchvision.transforms as transforms

#/********** Begin *********/
# 下载MNIST数据集
Mnist_dataset = dsets.MNIST(root='./data',train=True,transform=transforms.ToTensor(),
download=True)
# 创建batch_size=100, shuffle=True的DataLoader类型的变量data_loader
data_loader = torch.utils.data.DataLoader(dataset=Mnist_dataset,
                                          batch_size=100,
                                          shuffle=True)
#输出 data_loader中数据类型
print(type(data_loader.dataset))
#/********** End *********/

第2关：建立模型，定义损失和优化函数

import torch.nn as nn
#/********** Begin *********/
# 线性回归模型
class LinearRegression(nn.Module):
    def __init__(self):
        # 调用Module的初始化
        super(LinearRegression, self).__init__()
        # 输入和输出分别为一维
        self.linear = nn.Linear(1, 1)
    # module调用forward，将按forward进行前向传播，并构建网络
    def forward(self, x):
        out = self.linear(x)
        return out
# 实例化一个新建的模型变量model
model = LinearRegression()
# 输出该模型 model 的‘.parameters'属性
print(model.parameters)
#/********** End *********/

第3关：训练模型


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

import os
import sys
path = os.path.split(os.path.abspath(os.path.realpath(sys.argv[0])))[0] + os.path.sep

print(path)

# 超参数
input_size = 1
output_size = 1
num_epochs = 60
learning_rate = 0.001

# 数据集
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)

# 线性回归模型
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)
        return out

model = LinearRegression(input_size, output_size)


#创建输出文件 output.txt
f = open(path + 'output.txt', 'w')
f.seek(0)
f.truncate()   #清空文件

#/********** Begin *********/ 
# 创建损失函数MSELoss
criterion = nn.MSELoss()
# 创建SGD的Optimizer，学习率l'r为0.001
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
# 训练模型
for epoch in range(num_epochs):
    # 将x_train，y_train数据转换为Variable类型
    inputs = Variable(torch.from_numpy(x_train))
    targets = Variable(torch.from_numpy(y_train))
    # Forward
    optimizer.zero_grad()
    outputs = model(inputs)
    loss = criterion(outputs, targets)
    # Backward
    loss.backward()
    #Optimize
    optimizer.step()
    #共训练60次，分别10次输出一回loss信息，并将输出信息存到文件中
    
    if (epoch+1) % 10 == 0:
        f.writelines('Epoch [%d/%d], Loss: %.4f \n'%(epoch+1, num_epochs, loss.data[0]))
        print ('Epoch [%d/%d], Loss: %.4f'
                   %(epoch+1, num_epochs, loss.data[0]))
f.close()

#/********** End *********/

#保存模型
torch.save(model,path + 'model.pkl')

第4关：validation

import torch
import numpy as np
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt

from torch.autograd import Variable
import torch.nn as nn

import warnings
warnings.filterwarnings('ignore')

import os,sys
path = os.path.split(os.path.abspath(os.path.realpath(sys.argv[0])))[0] + os.path.sep
path = path[:-6]
print("validation path:" ,path)

# Linear Regression Model
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)
        return out

model = LinearRegression(1, 1)


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)

#加载整个模型
model = torch.load( path + 'step3/model.pkl')

#/********** Begin *********/
#将模型转化为测试模式
#将模型转化为测试模式
model.eval()
#利用 model 计算预测值
predicted = model(Variable(torch.from_numpy(x_train))).data.numpy()
print(predicted)
#画图
plt.plot(x_train, y_train, 'ro', label='Original data')
plt.plot(x_train, predicted, label='Fitted line')
plt.legend()
plt.savefig(path + "step4/outputimages/mylossTest.png")

#/********** End *********/

文章来源地址https://www.toymoban.com/news/detail-526364.html

到了这里，关于PyTorch之线性回归的文章就介绍完了。如果您还想了解更多内容，请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章，希望大家以后多多支持TOY模板网！