[{"createTime":1735734952000,"id":1,"img":"hwy_ms_500_252.jpeg","link":"https://activity.huaweicloud.com/cps.html?fromacct=261f35b6-af54-4511-a2ca-910fa15905d1&utm_source=V1g3MDY4NTY=&utm_medium=cps&utm_campaign=201905","name":"华为云秒杀","status":9,"txt":"华为云38元秒杀","type":1,"updateTime":1735747411000,"userId":3},{"createTime":1736173885000,"id":2,"img":"txy_480_300.png","link":"https://cloud.tencent.com/act/cps/redirect?redirect=1077&cps_key=edb15096bfff75effaaa8c8bb66138bd&from=console","name":"腾讯云秒杀","status":9,"txt":"腾讯云限量秒杀","type":1,"updateTime":1736173885000,"userId":3},{"createTime":1736177492000,"id":3,"img":"aly_251_140.png","link":"https://www.aliyun.com/minisite/goods?userCode=pwp8kmv3","memo":"","name":"阿里云","status":9,"txt":"阿里云2折起","type":1,"updateTime":1736177492000,"userId":3},{"createTime":1735660800000,"id":4,"img":"vultr_560_300.png","link":"https://www.vultr.com/?ref=9603742-8H","name":"Vultr","status":9,"txt":"Vultr送$100","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":5,"img":"jdy_663_320.jpg","link":"https://3.cn/2ay1-e5t","name":"京东云","status":9,"txt":"京东云特惠专区","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":6,"img":"new_ads.png","link":"https://www.iodraw.com/ads","name":"发布广告","status":9,"txt":"发布广告","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":7,"img":"yun_910_50.png","link":"https://activity.huaweicloud.com/discount_area_v5/index.html?fromacct=261f35b6-af54-4511-a2ca-910fa15905d1&utm_source=aXhpYW95YW5nOA===&utm_medium=cps&utm_campaign=201905","name":"底部","status":9,"txt":"高性能云服务器2折起","type":2,"updateTime":1735660800000,"userId":3}]
回顾一下numpy训练逻辑回归模型的过程:
* 数据准备,参数初始化
* 前向计算
* 计算损失
* 计算梯度
* 更新参数
* 重复2至5步,观察损失函数值,调整学习率
pytorch提供了大量的封装好的计算函数,所以实现起来变得更加简洁和明了。
下面我们一步步地分解pytorch的逻辑回归实现
1. 数据准备,初始化参数
import torch from sklearn.datasets import load_iris data, target =
load_iris(return_X_y=True) x = torch.tensor(data[50:150], dtype=torch.float32)
# 指定输入x y = torch.tensor(target[:100], dtype=torch.float32).reshape(100,1) #
指定输入y w = torch.randn(1, 4, requires_grad=True) # 初始化参数w b = torch.randn(1,
requires_grad=True) # 初始化参数b learn_rate = 0.01 # 学习率 n_iters = 5000 # 最大迭代次数
2. 前向计算
y_ = torch.nn.functional.linear(input=x, weight=w, bias=b) # 计算线性输出 sy_ =
torch.sigmoid(y_) # 计算逻辑分布运算(输出的值可以作为概率使用)
pytorch的线性计算($Wx+b$)已经被封装到了torch.nn.functional.linear中,可以直接调用。sigmoid也有torch的实现。
3. 计算损失
# 损失函数 loss_mean = torch.nn.functional.binary_cross_entropy(sy_, y,
reduction="mean")
逻辑回归中的损失函数,也成之为交叉熵损失
$Loss =\sum\limits_{i \in \text{数据集}}y_i\ ln(h(x_i)) +(1-y_i)\ln(1-h(x_i))$
4. 计算梯度
梯度计算通过损失函数的backward自动完成。梯度值自动保存在变量$W$和$b$中。
# backward:计算梯度 loss_mean.backward()
5. 更新参数
with torch.autograd.no_grad(): # 关闭梯度计算跟踪 w -= learn_rate * w.grad # 更新权重梯度
w.grad.zero_() # 清空本次计算的梯度(因为梯度是累加计算,不清空就累加) b -= learn_rate * b.grad # 更新偏置项梯度
b.grad.zero_() # 清空本次计算的梯度
完整代码实现