1)设计模型: Design model (input, output, forward passwith different layers)2) 构建损失函数与优化器:Construct loss and optimizer
3) 循环:Training loop
- Forward = compute prediction and loss
- Backward = compute gradients
- Update weights
2.Pytorch搭建线性逻辑模型
2.1.导入必要模块
import torch
import torch.nn as nn
import numpy as np
from sklearn import datasets
from sklearn.preprocessing import StandardScaler #数据标准化模块from sklearn.model_selection import train_test_split
文章目录1.计算流程2.Pytorch搭建线性逻辑模型2.1.导入必要模块2.2.数据准备2.3.构建模型2.4.训练+计算准确率1.计算流程 1)设计模型: Design model (input, output, forward pass with different layers) 2) 构建损失函数与优化器:Construct loss and optimizer 3) 循环...