Datawhale_Task3 PyTorch实现Logistic regression
- PyTorch基础实现代码
- 用PyTorch类实现Logistic regression,torch.nn.module写网络结构
(1)什么是逻辑回归
分类和回归是机器学习可以解决两大主要问题,从预测值的类型上看,连续变量预测的定量输出称为回归;离散变量预测的定性输出称为分类。逻辑回归是一种广义的线性回归,逻辑回归虽然带有回归字样,名为回归,实属分类算法。通常用作二分类问题。线性回归完成的是回归拟合任务,用一条线去拟合每个数据点;而对于分类任务,逻辑回归需要一条线,把不同类别的样本区分开来。
(2)pytorch实现逻辑回归
实现手写数字分类,数据处理见 PyTorch入门精简资料(一)
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
from torch.utils.data import Dataset
from torch.autograd import Variable
from PIL import Image
import numpy as np
import os
from datetime import datetime
from tensorboardX import SummaryWriter
class MyDataset(Dataset):
def __init__(self, txt_path, transform = None, target_transform = None):
fh = open(txt_path, 'r')
imgs = []
count=0
for line in fh:
line = line.rstrip()
words = line.split()
if count == 60001:
print(count,'words----------------',words[0],int(words[1]))
count += 1
imgs.append((words[0], int(words[1])))
self.imgs = imgs # 最主要就是要生成这个list, 然后DataLoader中给index,通过getitem读取图片数据
self.transform = transform
self.target_transform = target_transform
def __getitem__(self, index):
fn, label = self.imgs[index]
img = Image.open(fn).convert('L') # 像素值 0~255,在transfrom.totensor会除以255,使像素值变成 0~1
if self.transform is not None:
img = self.transform(img) # 在这里做transform,转为tensor等等