pytorch 自定义数据库

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/Chang_Shuang/article/details/84829163

from torch.utils import data
import os
from PIL import Image
from torchvision import transforms as T


transform = T.Compose([
    T.Resize(224),  # 缩放图片，保持长宽比不变，最短边为224px
    T.CenterCrop(224),  # 从图片中间切出224 × 224的图片
    T.ToTensor(),
    T.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])  # 标准化至[-1, -1]，规定均值和标准差
])


class DogCat(data.Dataset):
    def __init__(self, root, transforms=None):
        super(DogCat, self).__init__()
        imgs = os.listdir(root)
        self.imgs = [os.path.join(root, img) for img in imgs]
        self.transforms = transform

    def __getitem__(self, index):
        img_path = self.imgs[index]
        # dog->1, cat->0
        label = 1 if 'dog' in img_path.split('/')[-1] else 0
        data = Image.open(img_path)
        if self.transforms:
            data = self.transforms(data)
        return data, label

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


data = DogCat('/home/dell/桌面/kaggle/train')
for img, label in data:
    print(img.size(), label)

torch.Size([3, 224, 224]) 0
torch.Size([3, 224, 224]) 1
torch.Size([3, 224, 224]) 1
torch.Size([3, 224, 224]) 0
torch.Size([3, 224, 224]) 0
torch.Size([3, 224, 224]) 0
torch.Size([3, 224, 224]) 1
torch.Size([3, 224, 224]) 1
torch.Size([3, 224, 224]) 1
torch.Size([3, 224, 224]) 0
torch.Size([3, 224, 224]) 0