pytorch学习笔记3--回归问题

关注

原创最新推荐文章于 2026-06-25 12:05:30 发布 295 阅读 AI 写同款· GEO 优化 ›

pytorch学习笔记（八）：softmax回归的从零开始实现文章目录1. 获取和读取数据2. 初始化模型参数3. 实现softmax运算4. 定义模型5. 定义损失函数6. 计算分类准确率7. 训练模型8. 预测小结这一节我们来动手实现softmax回归。首先导入本节实现所需的包或模块。 import torch import torchvision import numpy as np import sys sys.path.append("..") # 为了导入上层目录的d2lzh_pytorch import d2lzh_pytorch as d2l 1. 阅读详情

          
            
          
          回归问题
linear regression
y∈[−∞,+∞]y \in [-\infty, +\infty]y∈[−∞,+∞]

logistics regression
把y值压缩到[0,1]，变为概率问题

代码：
loss=(WX+b−y)2loss = (WX+b-y)^2loss=(WX+b−y)2

代码实现如下：  def compute_error_for_line_given_points(b,w,points):
  	totalError = 0
  	for i in range(0,len(points)):
  		x = points[i,0]
  		y = points[i,1]
  		totalError += (y-(w*x+b)) ** 2
  	return totalError / float(len(points))
  ```

w′=w−lr∗∂loss∂ww&#x27; = w -lr * \frac{\partial loss}{\partial w}w′=w−lr∗∂w∂loss​def step_gradient(b_current,w_current,points,learningRate):
	b_gradient = 0
	w_gradient = 0
	N = float(len(points))
	for i in range(0,len(points)):
		x = point[i,0]
		y = point[i,1]
		b_gradient += -(2/N) * (y-(w_current * x) + b_current)
		w_gradient += -(2/N) * x * (y - ((w_current * x) + b_current))
	new_b = b_current - (learningRate * b_gradient)
	new_m = w_current - (learningRate * w_gradient)

Iterate to optimize	def gradient_descent_runner(points,starting_b,starting_m,learning_rate,num_iterations):
		b = starting_b
		m = starting_m
		for i in range(num_iterations):
			b, m = step_gradient(b,m,np.array(points),learning_rate)
		return [b,m]





        