Datawhale 零基础入门CV赛事-Task2 数据读取与数据扩增

数据扩增方法

    在深度学习中数据扩增方法非常重要，数据扩增可以增加训练集的样本，同时也可以有效缓解模型过拟合的情况，也可以给模型带来的更强的泛化能力

常见数据扩增方法

以torchvision为例，常见的数据扩增方法包括：
transforms.CenterCrop 对图片中心进行裁剪
transforms.ColorJitter 对图像颜色的对比度、饱和度和零度进行变换
transforms.FiveCrop 对图像四个角和中心进行裁剪得到五分图像
transforms.Grayscale 对图像进行灰度变换
transforms.Pad 使用固定值进行像素填充
transforms.RandomAffine 随机仿射变换
transforms.RandomCrop 随机区域裁剪
transforms.RandomHorizontalFlip 随机水平翻转
transforms.RandomRotation 随机旋转
transforms.RandomVerticalFlip 随机垂直翻转

读取数据dataloader

Dataset：对数据集的封装，提供索引方式的对数据样本进行读取
DataLoder：对Dataset进行封装，提供批量读取的迭代读取

class SVHNDataset(Dataset):
    def __init__(self, img_path, img_label, transform=None):
        self.img_path = img_path
        self.img_label = img_label 
        if transform is not None:
            self.transform = transform
        else:
            self.transform = None

    def __getitem__(self, index):
        img = Image.open(self.img_path[index]).convert('RGB')

        if self.transform is not None:
            img = self.transform(img)
        
        lbl = np.array(self.img_label[index], dtype=np.int)
        lbl = list(lbl)  + (5 - len(lbl)) * [10]
        return img, torch.from_numpy(np.array(lbl[:5]))

    def __len__(self):
        return len(self.img_path)

使用范例

data = SVHNDataset(train_path, train_label,
          transforms.Compose([
              # 缩放到固定尺寸
              transforms.Resize((64, 128)),

              # 随机颜色变换
              transforms.ColorJitter(0.2, 0.2, 0.2),

              # 加入随机旋转
              transforms.RandomRotation(5),

              # 将图片转换为pytorch 的tesntor
              # transforms.ToTensor(),

              # 对图像像素进行归一化
              # transforms.Normalize([0.485,0.456,0.406],[0.229,0.224,0.225])
            ]))

import os, sys, glob, shutil, json
import cv2

from PIL import Image
import numpy as np

import torch
from torch.utils.data.dataset import Dataset
import torchvision.transforms as transforms

class SVHNDataset(Dataset):
    def __init__(self, img_path, img_label, transform=None):
        self.img_path = img_path
        self.img_label = img_label 
        if transform is not None:
            self.transform = transform
        else:
            self.transform = None

    def __getitem__(self, index):
        img = Image.open(self.img_path[index]).convert('RGB')

        if self.transform is not None:
            img = self.transform(img)
        
        # 原始SVHN中类别10为数字0
        lbl = np.array(self.img_label[index], dtype=np.int)
        lbl = list(lbl)  + (5 - len(lbl)) * [10]
        
        return img, torch.from_numpy(np.array(lbl[:5]))

    def __len__(self):
        return len(self.img_path)

train_path = glob.glob('../input/train/*.png')
train_path.sort()
train_json = json.load(open('../input/train.json'))
train_label = [train_json[x]['label'] for x in train_json]

train_loader = torch.utils.data.DataLoader(
        SVHNDataset(train_path, train_label,
                   transforms.Compose([
                       transforms.Resize((64, 128)),
                       transforms.ColorJitter(0.3, 0.3, 0.2),
                       transforms.RandomRotation(5),
                       transforms.ToTensor(),
                       transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
            ])), 
    batch_size=10, # 每批样本个数
    shuffle=False, # 是否打乱顺序
    num_workers=10, # 读取的线程个数
)

for data in train_loader:
    break

参考大佬1