资讯专栏INFORMATION COLUMN

上云采购季！| 2核2G4M爆款云服务器低至59元/年，更有多台、长期优惠，快来选购！

立即前往
首页/文章专栏/【PyTorch基础教程1】线性模型（学不会来打我啊）

【PyTorch基础教程1】线性模型（学不会来打我啊）

djfml / 3805人阅读

摘要：文章目录一线性模型二绘图工具三作业一线性模型不要小看简单线性模型哈哈，虽然这讲我们还没正式用到，但是用到的前向传播损失函数两种绘图等方法在后面是很常用的。

文章目录

一、线性模型

不要小看简单线性模型哈哈，虽然这讲我们还没正式用到pytorch，但是用到的前向传播、损失函数、两种绘loss图等方法在后面是很常用的。
对下面的代码说明：

  • zip函数可以将x_data和y_data组合元组列表，在for循环中每次遍历就是对于列表中的每个元组。
  • 函数forward()中，有一个变量w。这个变量最终的值是从for循环中传入的。
</>复制代码 
  1. # -*- coding: utf-8 -*-"""Created on Tue Oct 12 14:30:13 2021@author: 86493"""import numpy as npimport matplotlib.pyplot as pltx_data = [1.0, 2.0, 3.0]y_data = [2.0, 4.0, 6.0]def forward(x):    return x * wdef loss(x, y):    y_pred = forward(x)    return (y_pred - y) * (y_pred - y)# 保存权重w_list = []# 保存权重的损失函数值mse_list = []# 穷举w值对应的损失函数MSEfor w in np.arange(0.0, 4.1, 0.1):    print("w = ", w)    loss_sum = 0    for x_val, y_val in zip(x_data, y_data):        # 为了打印y预测值，其实loss里也计算了        y_pred_val = forward(x_val)        loss_val = loss(x_val, y_val)        loss_sum += loss_val        print("/t", x_val, y_val,              y_pred_val, loss_val)    print("MSE = ", loss_sum / 3)    print("="*60)    w_list.append(w)    mse_list.append(loss_sum / 3)     # 绘loss变化图，横坐标是w，纵坐标是lossplt.plot(w_list, mse_list)plt.ylabel("Loss")plt.xlabel("w")plt.show()

刚才对应的打印结果为：

</>复制代码 
  1. w =  0.0
  2.  1.0 2.0 0.0 4.0
  3.  2.0 4.0 0.0 16.0
  4.  3.0 6.0 0.0 36.0MSE =  18.666666666666668============================================================w =  0.1
  5.  1.0 2.0 0.1 3.61
  6.  2.0 4.0 0.2 14.44
  7.  3.0 6.0 0.30000000000000004 32.49MSE =  16.846666666666668============================================================w =  0.2
  8.  1.0 2.0 0.2 3.24
  9.  2.0 4.0 0.4 12.96
  10.  3.0 6.0 0.6000000000000001 29.160000000000004MSE =  15.120000000000003============================================================w =  0.30000000000000004
  11.  1.0 2.0 0.30000000000000004 2.8899999999999997
  12.  2.0 4.0 0.6000000000000001 11.559999999999999
  13.  3.0 6.0 0.9000000000000001 26.009999999999998MSE =  13.486666666666665============================================================w =  0.4
  14.  1.0 2.0 0.4 2.5600000000000005
  15.  2.0 4.0 0.8 10.240000000000002
  16.  3.0 6.0 1.2000000000000002 23.04MSE =  11.946666666666667============================================================w =  0.5
  17.  1.0 2.0 0.5 2.25
  18.  2.0 4.0 1.0 9.0
  19.  3.0 6.0 1.5 20.25MSE =  10.5============================================================w =  0.6000000000000001
  20.  1.0 2.0 0.6000000000000001 1.9599999999999997
  21.  2.0 4.0 1.2000000000000002 7.839999999999999
  22.  3.0 6.0 1.8000000000000003 17.639999999999993MSE =  9.146666666666663============================================================w =  0.7000000000000001
  23.  1.0 2.0 0.7000000000000001 1.6899999999999995
  24.  2.0 4.0 1.4000000000000001 6.759999999999998
  25.  3.0 6.0 2.1 15.209999999999999MSE =  7.886666666666666============================================================w =  0.8
  26.  1.0 2.0 0.8 1.44
  27.  2.0 4.0 1.6 5.76
  28.  3.0 6.0 2.4000000000000004 12.959999999999997MSE =  6.719999999999999============================================================w =  0.9
  29.  1.0 2.0 0.9 1.2100000000000002
  30.  2.0 4.0 1.8 4.840000000000001
  31.  3.0 6.0 2.7 10.889999999999999MSE =  5.646666666666666============================================================w =  1.0
  32.  1.0 2.0 1.0 1.0
  33.  2.0 4.0 2.0 4.0
  34.  3.0 6.0 3.0 9.0MSE =  4.666666666666667============================================================w =  1.1
  35.  1.0 2.0 1.1 0.8099999999999998
  36.  2.0 4.0 2.2 3.2399999999999993
  37.  3.0 6.0 3.3000000000000003 7.289999999999998MSE =  3.779999999999999============================================================w =  1.2000000000000002
  38.  1.0 2.0 1.2000000000000002 0.6399999999999997
  39.  2.0 4.0 2.4000000000000004 2.5599999999999987
  40.  3.0 6.0 3.6000000000000005 5.759999999999997MSE =  2.986666666666665============================================================w =  1.3
  41.  1.0 2.0 1.3 0.48999999999999994
  42.  2.0 4.0 2.6 1.9599999999999997
  43.  3.0 6.0 3.9000000000000004 4.409999999999998MSE =  2.2866666666666657============================================================w =  1.4000000000000001
  44.  1.0 2.0 1.4000000000000001 0.3599999999999998
  45.  2.0 4.0 2.8000000000000003 1.4399999999999993
  46.  3.0 6.0 4.2 3.2399999999999993MSE =  1.6799999999999995============================================================w =  1.5
  47.  1.0 2.0 1.5 0.25
  48.  2.0 4.0 3.0 1.0
  49.  3.0 6.0 4.5 2.25MSE =  1.1666666666666667============================================================w =  1.6
  50.  1.0 2.0 1.6 0.15999999999999992
  51.  2.0 4.0 3.2 0.6399999999999997
  52.  3.0 6.0 4.800000000000001 1.4399999999999984MSE =  0.746666666666666============================================================w =  1.7000000000000002
  53.  1.0 2.0 1.7000000000000002 0.0899999999999999
  54.  2.0 4.0 3.4000000000000004 0.3599999999999996
  55.  3.0 6.0 5.1000000000000005 0.809999999999999MSE =  0.4199999999999995============================================================w =  1.8
  56.  1.0 2.0 1.8 0.03999999999999998
  57.  2.0 4.0 3.6 0.15999999999999992
  58.  3.0 6.0 5.4 0.3599999999999996MSE =  0.1866666666666665============================================================w =  1.9000000000000001
  59.  1.0 2.0 1.9000000000000001 0.009999999999999974
  60.  2.0 4.0 3.8000000000000003 0.0399999999999999
  61.  3.0 6.0 5.7 0.0899999999999999MSE =  0.046666666666666586============================================================w =  2.0
  62.  1.0 2.0 2.0 0.0
  63.  2.0 4.0 4.0 0.0
  64.  3.0 6.0 6.0 0.0MSE =  0.0============================================================w =  2.1
  65.  1.0 2.0 2.1 0.010000000000000018
  66.  2.0 4.0 4.2 0.04000000000000007
  67.  3.0 6.0 6.300000000000001 0.09000000000000043MSE =  0.046666666666666835============================================================w =  2.2
  68.  1.0 2.0 2.2 0.04000000000000007
  69.  2.0 4.0 4.4 0.16000000000000028
  70.  3.0 6.0 6.6000000000000005 0.36000000000000065MSE =  0.18666666666666698============================================================w =  2.3000000000000003
  71.  1.0 2.0 2.3000000000000003 0.09000000000000016
  72.  2.0 4.0 4.6000000000000005 0.36000000000000065
  73.  3.0 6.0 6.9 0.8100000000000006MSE =  0.42000000000000054============================================================w =  2.4000000000000004
  74.  1.0 2.0 2.4000000000000004 0.16000000000000028
  75.  2.0 4.0 4.800000000000001 0.6400000000000011
  76.  3.0 6.0 7.200000000000001 1.4400000000000026MSE =  0.7466666666666679============================================================w =  2.5
  77.  1.0 2.0 2.5 0.25
  78.  2.0 4.0 5.0 1.0
  79.  3.0 6.0 7.5 2.25MSE =  1.1666666666666667============================================================w =  2.6
  80.  1.0 2.0 2.6 0.3600000000000001
  81.  2.0 4.0 5.2 1.4400000000000004
  82.  3.0 6.0 7.800000000000001 3.2400000000000024MSE =  1.6800000000000008============================================================w =  2.7
  83.  1.0 2.0 2.7 0.49000000000000027
  84.  2.0 4.0 5.4 1.960000000000001
  85.  3.0 6.0 8.100000000000001 4.410000000000006MSE =  2.2866666666666693==========================================           
  86.                
  87.                                            
  88.                        
  89.
云服务器 GPU云服务器 python线性模型 非线性模型r语言 学算法不会Java 学php的不会做前台

文章版权归作者所有，未经允许请勿转载,若此文章存在违规行为，您可以联系管理员删除。

转载请注明本文地址：https://www.ucloud.cn/yun/122570.html

相关文章

  • 转行测试的看过来！0基础~自动化测试，我整理的超全学习指南...

    摘要：在这个阶段，学习工具什么的，重点在于接口测试的学习，所有的工具的学习，都是在为了接口测试的学习做铺垫。接口测试工具的使用。 很多朋友想要入行软件测试，但是都不知道该怎么学。 抽个时间简单的给大家说下，对于0基础的朋友，应该怎么去学习软件测试。 学习软件测试有2条路可以选。 最省事的当然是找个...

    Hanks10100 评论0 收藏0

  • 第7期 Datawhale 组队学习计划

    马上就要开始啦这次共组织15个组队学习 涵盖了AI领域从理论知识到动手实践的内容 按照下面给出的最完备学习路线分类 难度系数分为低、中、高三档 可以按照需要参加 - 学习路线 - showImg(https://segmentfault.com/img/remote/1460000019082128); showImg(https://segmentfault.com/img/remote/...

    dinfer 评论0 收藏0

  • ApacheCN 编程/大数据/数据科学/人工智能学习资源 2019.6

    摘要：请回复这个帖子并注明组织个人信息来申请加入。权限分配灵活，能者居之。数量超过个，在所有组织中排名前。网站日超过，排名的峰值为。导航归档社区自媒体平台微博知乎专栏公众号博客园简书合作侵权，请联系请抄送一份到赞助我们 Special Sponsors showImg(https://segmentfault.com/img/remote/1460000018907426?w=1760&h=...

    Bmob 评论0 收藏0

发表评论

登陆后可评论

0条评论

djfml

男|高级讲师
我要私信

TA的文章

阅读更多
最新活动
阅读需要支付1元查看
<