学习笔记——6-5加载cifar10数据集

#自定义加载cifar10数据集
from torchvision import transforms
from torch.utils.data import DataLoader, Dataset
import os
from PIL import Image
import numpy as np
import glob

label_name = ["airplane", "automobile", "bird",
              "cat", "deer", "dog",
              "frog", "horse", "ship", "truck"]

label_dict = {}

for idx, name in enumerate(label_name):
    label_dict[name] = idx

def default_loader(path):
    return Image.open(path).convert("RGB")

train_transform = transforms.Compose([
    transforms.RandomResizedCrop((28, 28)),
    transforms.RandomHorizontalFlip(),
    transforms.RandomVerticalFlip(),
    transforms.RandomRotation(90),
    transforms.RandomGrayscale(0.2),
    transforms.ColorJitter(0.1, 0.1, 0.1, 0.1),
    transforms.ToTensor()
])

test_transform = transforms.Compose([
    transforms.Resize((28, 28)),
    transforms.ToTensor()
])

class MyDataset(Dataset):
    def __init__(self, im_list,
                 transform=None,
                 loader = default_loader):
        super(MyDataset, self).__init__()
        imgs = []

        for im_item in im_list:
            #"/home/kuan/dataset/CIFAR10/TRAIN/" \
            #"airplane/aeroplane_s_000021.png"
            #注意分割路径的中间符号到底是什么。。linux和windows符号不一样的
            im_label_name = im_item.split("\\")[-2]
            #print(im_label_name)
            imgs.append([im_item, label_dict[im_label_name]])

        self.imgs = imgs
        self.transform = transform
        self.loader = loader

    def __getitem__(self, index):
        im_path, im_label = self.imgs[index]
        im_data = self.loader(im_path)
        if self.transform is not None:
            im_data = self.transform(im_data)

        return im_data, im_label

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


im_train_list = glob.glob("D:/good good study/data analyse/dataset/train/*/*.png")
im_test_list = glob.glob("D:/good good study/data analyse/dataset/test/*/*.png")

train_dataset=MyDataset(im_train_list,
                        transform=train_transform)
test_dataset=MyDataset(im_test_list,
                       transform=test_transform)

train_data_loader = DataLoader(dataset=train_dataset,
                               batch_size=6,
                               shuffle=True,
                               num_workers=4)
test_data_loader = DataLoader(dataset=test_dataset,
                              batch_size=6,
                              shuffle=False,
                              num_workers=4)
print("nmu_of_train", len(train_dataset))
print("nmu_of_test", len(test_dataset))

输出结果：

nmu_of_train 50000
nmu_of_test 10000