PyTorch如何创建自己的数据集

class ImageFolder(Dataset):
    def __init__(self, folder_path):
        self.files = sorted(glob.glob('%s/*.*' % folder_path))

    def __getitem__(self, index):
        path = self.files[index % len(self.files)]
        img = np.array(Image.open(path))
        h, w, c = img.shape
        pad = ((40, 40), (4, 4), (0, 0))

        # img = np.pad(img, pad, 'constant', constant_values=0) / 255
        img = np.pad(img, pad, mode='edge') / 255.0
        img = torch.from_numpy(img).float()
        patches = np.reshape(img, (3, 10, 128, 11, 128))
        patches = np.transpose(patches, (0, 1, 3, 2, 4))

        return img, patches, path

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

self.files = sorted(glob.glob('%s/**/*.*' % folder_path, recursive=True))

from torch.utils.tensorboard import SummaryWriter
from torchvision.transforms import Compose
from torchvision import transforms
import torchvision
import ssl

ssl._create_default_https_context = ssl._create_unverified_context

dataset_transform = Compose([transforms.ToTensor()])


# 关于官方数据集的使用还是关键要看pytorch的官方文档
train_set = torchvision.datasets.CIFAR10(root="./CIFAR10",train=True,transform=dataset_transform,download=True)
test_set = torchvision.datasets.CIFAR10(root="./CIFAR10",train=False,transform=dataset_transform,download=True)

# 查看测试数据集中的第一个数据
# print(test_set[0])
# 查看测试数据集中的分类情况
# print(test_set.classes)
#
# 取出第一个数据中的图片（img）和分类结果（target）
# img,target = test_set[0]
# 查看图片数据的类型
# print(img)
# print(target)
# 输出类别
# print(test_set.classes[target])
# 查看图片
# img.show()

# 使用tensorboard显示tensor数据类型的图片
writer = SummaryWriter("logs")
for i in range(10):
	# 取出数据中的图片（img）和分类结果（target）
    img,target = test_set[i]
    writer.add_image("test_set",img,i)

writer.close()

train_set = torchvision.datasets.CIFAR10(root="./CIFAR10",train=True,transform=dataset_transform,download=True)