Как загрузить набор данных CelebA в Google Colab с помощью Torch Vision, не исчерпывая памяти?

Решить проблему с памятью не удалось. Однако я придумал обходной путь — настраиваемый набор данных. Вот моя реализация:

import os
import zipfile 
import gdown
import torch
from natsort import natsorted
from PIL import Image
from torch.utils.data import Dataset
from torchvision import transforms

## Setup
# Number of gpus available
ngpu = 1
device = torch.device('cuda:0' if (
    torch.cuda.is_available() and ngpu > 0) else 'cpu')

## Fetch data from Google Drive 
# Root directory for the dataset
data_root = 'data/celeba'
# Path to folder with the dataset
dataset_folder = f'{data_root}/img_align_celeba'
# URL for the CelebA dataset
url = 'https://drive.google.com/uc?id=1cNIac61PSA_LqDFYFUeyaQYekYPc75NH'
# Path to download the dataset to
download_path = f'{data_root}/img_align_celeba.zip'

# Create required directories 
if not os.path.exists(data_root):
  os.makedirs(data_root)
  os.makedirs(dataset_folder)

# Download the dataset from google drive
gdown.download(url, download_path, quiet=False)

# Unzip the downloaded file 
with zipfile.ZipFile(download_path, 'r') as ziphandler:
  ziphandler.extractall(dataset_folder)

## Create a custom Dataset class
class CelebADataset(Dataset):
  def __init__(self, root_dir, transform=None):
    """
    Args:
      root_dir (string): Directory with all the images
      transform (callable, optional): transform to be applied to each image sample
    """
    # Read names of images in the root directory
    image_names = os.listdir(root_dir)

    self.root_dir = root_dir
    self.transform = transform 
    self.image_names = natsorted(image_names)

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

  def __getitem__(self, idx):
    # Get the path to the image 
    img_path = os.path.join(self.root_dir, self.image_names[idx])
    # Load image and convert it to RGB
    img = Image.open(img_path).convert('RGB')
    # Apply transformations to the image
    if self.transform:
      img = self.transform(img)

    return img

## Load the dataset 
# Path to directory with all the images
img_folder = f'{dataset_folder}/img_align_celeba'
# Spatial size of training images, images are resized to this size.
image_size = 64
# Transformations to be applied to each individual image sample
transform=transforms.Compose([
    transforms.Resize(image_size),
    transforms.CenterCrop(image_size),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.5, 0.5, 0.5],
                          std=[0.5, 0.5, 0.5])
])
# Load the dataset from file and apply transformations
celeba_dataset = CelebADataset(img_folder, transform)

## Create a dataloader 
# Batch size during training
batch_size = 128
# Number of workers for the dataloader
num_workers = 0 if device.type == 'cuda' else 2
# Whether to put fetched data tensors to pinned memory
pin_memory = True if device.type == 'cuda' else False

celeba_dataloader = torch.utils.data.DataLoader(celeba_dataset,
                                                batch_size=batch_size,
                                                num_workers=num_workers,
                                                pin_memory=pin_memory,
                                                shuffle=True)

Эта реализация эффективна с точки зрения памяти и работает для моего случая использования, даже во время обучения использованная память в среднем составляет около (4 ГБ). Однако я был бы признателен за дополнительную интуицию относительно того, что могло вызвать проблемы с памятью.