PyTorch 深度学习之线性模型Linear model(一)

河图洛水

已于 2023-09-14 20:07:56 修改

阅读量836

点赞数

分类专栏：深度学习文章标签：深度学习人工智能 pytorch 线性回归

于 2022-03-28 23:05:33 首次发布

本文链接：https://blog.csdn.net/HETUW/article/details/123804784

版权

深度学习专栏收录该内容

11 篇文章 0 订阅

订阅专栏

一、步骤是什么？

1.DataSet

2.Model

3.Training

4.Inferring

P.S可能出现过拟合，可以使用Dev开发集提高泛化能力

二、线性模型基础（Linear model ）

A random guess-穷举法

2.1.Evaluate Model Error

training loss

$Loss=\left ( \widehat{y} -y\right )^{2}=\left ( x*w -y\right )^{2}$

2.2.MSE (Mean Square Error)

$Cost=\frac{1}{N}\sum\textup{} \left ( \widehat{y} -y\right )^{2}$

平均平方误差

三、代码操作(穷举法)

1.f(x)=w*x

import numpy as np
import matplotlib.pyplot as plt
 
x_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]
 
 
def forward(x):
    return x*w
 
 
def loss(x, y):
    y_pred = forward(x)
    return (y_pred - y)*(y_pred - y)
 
 
w_list = []
mse_list = []
for w in np.arange(0.0, 4.1, 0.1):
    print("w=", w)
    l_sum = 0
    for x_val, y_val in zip(x_data, y_data):
        y_pred_val = forward(x_val)
        loss_val = loss(x_val, y_val)
        l_sum += loss_val
        print('\t', x_val, y_val, y_pred_val, loss_val)
    print('MSE=', l_sum/3)
    w_list.append(w)
    mse_list.append(l_sum/3)
    
plt.plot(w_list,mse_list)
plt.ylabel('Loss')
plt.xlabel('w')
plt.show()

结果展示

P.S:zip()用法

>>> a = [1,2,3]
>>> b = [4,5,6]
>>> c = [4,5,6,7,8]
>>> zipped = zip(a,b)     # 打包为元组的列表
[(1, 4), (2, 5), (3, 6)]
>>> zip(a,c)              # 元素个数与最短的列表一致
[(1, 4), (2, 5), (3, 6)]
>>> zip(*zipped)          # 与 zip 相反，*zipped 可理解为解压，返回二维矩阵式
[(1, 2, 3), (4, 5, 6)]

2.f(x)=w*x+b(双参数)

import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D

#函数为y=4x+2
x_data = [1.0,2.0,3.0]
y_data = [6.0,10.0,14.0]

def forward(x):
    return x * w + b

def loss(x,y):
    y_pred = forward(x)
    return (y_pred-y)*(y_pred-y)

mse_list = []
W=np.arange(0.0,4.1,0.1)
B=np.arange(0.0,4.1,0.1)
[w,b]=np.meshgrid(W,B)

l_sum = 0
for x_val, y_val in zip(x_data, y_data):
    y_pred_val = forward(x_val)
    print(y_pred_val)
    loss_val = loss(x_val, y_val)
    l_sum += loss_val

fig = plt.figure()
ax = Axes3D(fig)
ax.plot_surface(w, b, l_sum/3)
plt.show()