clarena.cl_datasets.split_cifar100

  1r"""
  2The submodule in `cl_datasets` for Split CIFAR-100 dataset.
  3"""
  4
  5__all__ = ["SplitCIFAR100"]
  6
  7import logging
  8from typing import Callable
  9
 10import torch
 11from torch.utils.data import Dataset, random_split
 12from torchvision.datasets import CIFAR100
 13from torchvision.transforms import transforms
 14
 15from clarena.cl_datasets import CLSplitDataset
 16
 17# always get logger for built-in logging in each module
 18pylogger = logging.getLogger(__name__)
 19
 20
 21class SplitCIFAR100(CLSplitDataset):
 22    r"""Split CIFAR-100 dataset. The [CIFAR-100 dataset](https://www.cs.toronto.edu/~kriz/cifar.html) is a subset of the [80 million tiny images dataset](https://people.csail.mit.edu/torralba/tinyimages/). It consists of 50,000 training and 10,000 test images of 100 classes, each 32x32 color image."""
 23
 24    original_dataset_python_class: type[Dataset] = CIFAR100
 25    r"""The original dataset class."""
 26
 27    def __init__(
 28        self,
 29        root: str,
 30        class_split: dict[int, list[int]],
 31        validation_percentage: float,
 32        batch_size: int | dict[int, int] = 1,
 33        num_workers: int | dict[int, int] = 0,
 34        custom_transforms: (
 35            Callable
 36            | transforms.Compose
 37            | None
 38            | dict[int, Callable | transforms.Compose | None]
 39        ) = None,
 40        repeat_channels: int | None | dict[int, int | None] = None,
 41        to_tensor: bool | dict[int, bool] = True,
 42        resize: tuple[int, int] | None | dict[int, tuple[int, int] | None] = None,
 43    ) -> None:
 44        r"""
 45        **Args:**
 46        - **root** (`str`): the root directory where the original CIFAR-100 data 'cifar-100-python/' live.
 47        - **class_split** (`dict[int, list[int]]`): the dict of classes for each task. The keys are task IDs ane the values are lists of class labels (integers starting from 0) to split for each task.
 48        - **validation_percentage** (`float`): The percentage to randomly split some training data into validation data.
 49        - **batch_size** (`int` | `dict[int, int]`): the batch size for train, val, and test dataloaders.
 50        If it is a dict, the keys are task IDs and the values are the batch sizes for each task. If it is an `int`, it is the same batch size for all tasks.
 51        - **num_workers** (`int` | `dict[int, int]`): the number of workers for dataloaders.
 52        If it is a dict, the keys are task IDs and the values are the number of workers for each task. If it is an `int`, it is the same number of workers for all tasks.
 53        - **custom_transforms** (`transform` or `transforms.Compose` or `None` or dict of them): the custom transforms to apply ONLY to the TRAIN dataset. Can be a single transform, composed transforms, or no transform. `ToTensor()`, normalization, permute, and so on are not included.
 54        If it is a dict, the keys are task IDs and the values are the custom transforms for each task. If it is a single transform or composed transforms, it is applied to all tasks. If it is `None`, no custom transforms are applied.
 55        - **repeat_channels** (`int` | `None` | dict of them): the number of channels to repeat for each task. Default is `None`, which means no repeat.
 56        If it is a dict, the keys are task IDs and the values are the number of channels to repeat for each task. If it is an `int`, it is the same number of channels to repeat for all tasks. If it is `None`, no repeat is applied.
 57        - **to_tensor** (`bool` | `dict[int, bool]`): whether to include the `ToTensor()` transform. Default is `True`.
 58        If it is a dict, the keys are task IDs and the values are whether to include the `ToTensor()` transform for each task. If it is a single boolean value, it is applied to all tasks.
 59        - **resize** (`tuple[int, int]` | `None` or dict of them): the size to resize the images to. Default is `None`, which means no resize.
 60        If it is a dict, the keys are task IDs and the values are the sizes to resize for each task. If it is a single tuple of two integers, it is applied to all tasks. If it is `None`, no resize is applied.
 61        """
 62
 63        super().__init__(
 64            root=root,
 65            class_split=class_split,
 66            batch_size=batch_size,
 67            num_workers=num_workers,
 68            custom_transforms=custom_transforms,
 69            repeat_channels=repeat_channels,
 70            to_tensor=to_tensor,
 71            resize=resize,
 72        )
 73
 74        self.validation_percentage: float = validation_percentage
 75        r"""The percentage to randomly split some training data into validation data."""
 76
 77    def prepare_data(self) -> None:
 78        r"""Download the original CIFAR-100 dataset if haven't."""
 79
 80        if self.task_id != 1:
 81            return  # download all original datasets only at the beginning of first task
 82
 83        CIFAR100(root=self.root_t, train=True, download=True)
 84        CIFAR100(root=self.root_t, train=False, download=True)
 85
 86        pylogger.debug(
 87            "The original CIFAR-100 dataset has been downloaded to %s.", self.root
 88        )
 89
 90    def get_subset_of_classes(self, dataset: Dataset) -> Dataset:
 91        r"""Get a subset of classes from the dataset of current classes of `self.task_id`. It is used when constructing the split. It must be implemented by subclasses.
 92
 93        **Args:**
 94        - **dataset** (`Dataset`): the dataset to retrieve subset from.
 95
 96        **Returns:**
 97        - **subset** (`Dataset`): the subset of classes from the dataset.
 98        """
 99        classes = self.class_split[self.task_id]
100
101        # get the indices of the dataset that belong to the classes
102        idx = [i for i, (_, target) in enumerate(dataset) if target in classes]
103
104        # subset the dataset by the indices, in-place operation
105        dataset.data = dataset.data[idx]  # data is a Numpy ndarray
106        dataset.targets = [dataset.targets[i] for i in idx]  # targets is a list
107
108        dataset.target_transform = self.target_transform()
109
110        return dataset
111
112    def train_and_val_dataset(self) -> tuple[Dataset, Dataset]:
113        r"""Get the training and validation dataset of task `self.task_id`.
114
115        **Returns:**
116        - **train_and_val_dataset** (`tuple[Dataset, Dataset]`): the train and validation dataset of task `self.task_id`.
117        """
118        dataset_train_and_val = self.get_subset_of_classes(
119            CIFAR100(
120                root=self.root_t,
121                train=True,
122                transform=self.train_and_val_transforms(),
123                # cl class mapping should be applied after the split
124                download=False,
125            )
126        )
127
128        return random_split(
129            dataset_train_and_val,
130            lengths=[1 - self.validation_percentage, self.validation_percentage],
131            generator=torch.Generator().manual_seed(
132                42
133            ),  # this must be set fixed to make sure the datasets across experiments are the same. Don't handle it to global seed as it might vary across experiments
134        )
135
136    def test_dataset(self) -> Dataset:
137        r"""Get the test dataset of task `self.task_id`.
138
139        **Returns:**
140        - **test_dataset** (`Dataset`): the test dataset of task `self.task_id`.
141        """
142        dataset_test = self.get_subset_of_classes(
143            CIFAR100(
144                root=self.root_t,
145                train=False,
146                transform=self.test_transforms(),
147                # cl class mapping should be applied after the split
148                download=False,
149            )
150        )
151
152        return dataset_test