clarena.cl_datasets.permuted_fer2013

  1r"""
  2The submodule in `cl_datasets` for Permuted FER2013 dataset.
  3"""
  4
  5__all__ = ["PermutedFER2013"]
  6
  7import logging
  8from typing import Callable
  9
 10import torch
 11from torch.utils.data import Dataset, random_split
 12from torchvision.datasets import FER2013
 13from torchvision.transforms import transforms
 14
 15from clarena.cl_datasets import CLPermutedDataset
 16
 17# always get logger for built-in logging in each module
 18pylogger = logging.getLogger(__name__)
 19
 20
 21class PermutedFER2013(CLPermutedDataset):
 22    r"""Permuted FER2013 dataset. The [FER2013 dataset](https://www.sciencedirect.com/science/article/abs/pii/S0893608014002159) is a collection of facial expression images. It consists of 35,887 images of 7 facial expressions (classes), each 48x48 grayscale image."""
 23
 24    original_dataset_python_class: type[Dataset] = FER2013
 25    r"""The original dataset class."""
 26
 27    def __init__(
 28        self,
 29        root: str,
 30        num_tasks: 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        permutation_mode: str = "first_channel_only",
 44        permutation_seeds: dict[int, int] | None = None,
 45    ) -> None:
 46        r"""
 47        **Args:**
 48        - **root** (`str`): the root directory where the original FER2013 data 'FER2013/' live.
 49        - **num_tasks** (`int`): the maximum number of tasks supported by the CL dataset. This decides the valid task IDs from 1 to `num_tasks`.
 50        - **validation_percentage** (`float`): the percentage to randomly split some training data into validation data.
 51        - **batch_size** (`int` | `dict[int, int]`): the batch size for train, val, and test dataloaders.
 52        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.
 53        - **num_workers** (`int` | `dict[int, int]`): the number of workers for dataloaders.
 54        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.
 55        - **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.
 56        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.
 57        - **repeat_channels** (`int` | `None` | dict of them): the number of channels to repeat for each task. Default is `None`, which means no repeat.
 58        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.
 59        - **to_tensor** (`bool` | `dict[int, bool]`): whether to include the `ToTensor()` transform. Default is `True`.
 60        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.
 61        - **resize** (`tuple[int, int]` | `None` or dict of them): the size to resize the images to. Default is `None`, which means no resize.
 62        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.
 63        - **permutation_mode** (`str`): the mode of permutation; one of:
 64            1. 'all': permute all pixels.
 65            2. 'by_channel': permute channel by channel separately. All channels are applied the same permutation order.
 66            3. 'first_channel_only': permute only the first channel.
 67        - **permutation_seeds** (`dict[int, int]` | `None`): the dict of seeds for permutation operations used to construct each task. Keys are task IDs and the values are permutation seeds for each task. Default is `None`, which creates a dict of seeds from 0 to `num_tasks`-1.
 68        """
 69
 70        super().__init__(
 71            root=root,
 72            num_tasks=num_tasks,
 73            batch_size=batch_size,
 74            num_workers=num_workers,
 75            custom_transforms=custom_transforms,
 76            repeat_channels=repeat_channels,
 77            to_tensor=to_tensor,
 78            resize=resize,
 79            permutation_mode=permutation_mode,
 80            permutation_seeds=permutation_seeds,
 81        )
 82
 83        self.validation_percentage: float = validation_percentage
 84        r"""The percentage to randomly split some training data into validation data."""
 85
 86    def prepare_data(self) -> None:
 87        r"""Download the original FER2013 dataset if haven't."""
 88
 89        if self.task_id != 1:
 90            return  # download all original datasets only at the beginning of first task
 91
 92        FER2013(root=self.root_t, split="train")
 93        FER2013(root=self.root_t, split="test")
 94
 95        pylogger.debug(
 96            "The original FER2013 dataset has been downloaded to %s.",
 97            self.root_t,
 98        )
 99
100    def train_and_val_dataset(self) -> tuple[Dataset, Dataset]:
101        """Get the training and validation dataset of task `self.task_id`.
102
103        **Returns:**
104        - **train_and_val_dataset** (`tuple[Dataset, Dataset]`): the train and validation dataset of task `self.task_id`.
105        """
106        dataset_train_and_val = FER2013(
107            root=self.root_t,
108            split="train",
109            transform=self.train_and_val_transforms(),
110            target_transform=self.target_transform(),
111        )
112
113        return random_split(
114            dataset_train_and_val,
115            lengths=[1 - self.validation_percentage, self.validation_percentage],
116            generator=torch.Generator().manual_seed(
117                42
118            ),  # 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
119        )
120
121    def test_dataset(self) -> Dataset:
122        r"""Get the test dataset of task `self.task_id`.
123
124        **Returns:**
125        - **test_dataset** (`Dataset`): the test dataset of task `self.task_id`.
126        """
127        dataset_test = FER2013(
128            root=self.root_t,
129            split="test",
130            transform=self.test_transforms(),
131            target_transform=self.target_transform(),
132        )
133
134        return dataset_test