PyTorch-数据处理流程

import os
import pandas as pd
from torchvision.io import read_image

class CustomImageDataset(Dataset):
    def __init__(self, annotations_file, img_dir, transform=None, target_transform=None):
        self.img_labels = pd.read_csv(annotations_file)
        self.img_dir = img_dir
        self.transform = transform
        self.target_transform = target_transform

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

    def __getitem__(self, idx):
        img_path = os.path.join(self.img_dir, self.img_labels.iloc[idx, 0])
        image = read_image(img_path)
        label = self.img_labels.iloc[idx, 1]
        if self.transform:
            image = self.transform(image)
        if self.target_transform:
            label = self.target_transform(label)
        return image, label

class Sampler(Generic[T_co]):
    r"""Base class for all Samplers.

    Every Sampler subclass has to provide an :meth:`__iter__` method, providing a
    way to iterate over indices of dataset elements, and a :meth:`__len__` method
    that returns the length of the returned iterators.

    .. note:: The :meth:`__len__` method isn't strictly required by
              :class:`~torch.utils.data.DataLoader`, but is expected in any
              calculation involving the length of a :class:`~torch.utils.data.DataLoader`.
    """

    def __init__(self, data_source: Optional[Sized]) -> None:
        pass

    def __iter__(self) -> Iterator[T_co]:
        raise NotImplementedError

torch.utils.data.DataLoader(dataset, batch_size=1, 
          shuffle=False, sampler=None, batch_sampler=None, 
          num_workers=0, collate_fn=None, pin_memory=False, 
          drop_last=False, timeout=0, worker_init_fn=None, 
          multiprocessing_context=None, generator=None, *, 
          prefetch_factor=2, persistent_workers=False)