Datawhale零基础入门CV_Task2 数据读取与数据扩增

最新推荐文章于 2023-02-03 21:42:23 发布

sjtu_landon

最新推荐文章于 2023-02-03 21:42:23 发布

阅读量220

点赞数 1

分类专栏：零基础入门CV 文章标签： python 计算机视觉

本文链接：https://blog.csdn.net/LH294373770/article/details/106295456

版权

零基础入门CV 专栏收录该内容

5 篇文章 1 订阅

订阅专栏

1 思维导图

Task2思维导图

2 补充内容

Pytorch数据读取代码：

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([
                       # 缩放到固定尺寸
                   	   transforms.Resize((64, 128)),
                   	   # 随机颜色变换
                       transforms.ColorJitter(0.3, 0.3, 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])
            ])), 
    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