constants.py

LEADERBOARD_HEADER = """
<style>
.header-gradient {
    top: 40%;
    bottom: 40%;
    padding: 10px 0px;
    font-weight: bold;
    font-size: 40px;
    font-family: Inter, Arial, Helvetica, sans-serif;
    background: linear-gradient(to right, #FF705B, #FFB457);
    -webkit-text-fill-color: transparent;
    -webkit-background-clip: text;
}

.header-normal {
    top: 40%;
    bottom: 40%;
    padding: 10px 0px;
    font-weight: bold;
    font-size: 40px;
    font-family: Inter, Arial, Helvetica, sans-serif;
}
</style>

<div align="center">
    <span class="header-gradient"> DD-Ranking </span>
    <span class="header-normal"> Leaderboard </span>
</div>
<p align="center">
| <a href="https://nus-hpc-ai-lab.github.io/DD-Ranking/"><b>Documentation</b></a> | <a href="https://github.com/NUS-HPC-AI-Lab/DD-Ranking"><b>Github</b></a> | <a href=""><b>Paper </b> (Coming Soon)</a> | <a href=""><b>Twitter/X</b> (Coming Soon)</a> | <a href=""><b>Developer Slack</b> (Coming Soon)</a> |
</p>"""

LEADERBOARD_INTRODUCTION = """
# DD-Ranking Leaderboard

🏆 Welcome to the leaderboard of the **DD-Ranking**! 

> DD-Ranking (DD, i.e., Dataset Distillation) is an integrated and easy-to-use benchmark for dataset distillation. It aims to provide a fair evaluation scheme for DD methods that can decouple the impacts from knowledge distillation and data augmentation to reflect the real informativeness of the distilled data.

- **Fair Evaluation**: DD-Ranking provides a fair evaluation scheme for DD methods that can decouple the impacts from knowledge distillation and data augmentation to reflect the real informativeness of the distilled data.
- **Easy-to-use**: DD-Ranking provides a unified interface for dataset distillation evaluation.
- **Extensible**: DD-Ranking supports various datasets and models.
- **Customizable**: DD-Ranking supports various data augmentations and soft label strategies.

**Join Leaderboard**: Please see the [instructions](https://github.com/NUS-HPC-AI-Lab/DD-Ranking/blob/main/CONTRIBUTING.md) to participate.
"""

CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""
COMING SOON
"""

IPC_INFO = """
Images Per Class
"""

LABEL_TYPE_INFO = """
Hard labels are categorical, having the same format of the real dataset. Soft labels are generated by a teacher model pretrained on the target dataset
"""

WEIGHT_ADJUSTMENT_INTRODUCTION = """
The score for ranking (DD-Ranking Score, DDRS) in the following table is computed by $DDRS = \\frac{e^{w IOR - (1 - w) HLR} - e^{-1}}{e - e^{-1}}$, where $w$ is the weight for the HLR metric.
**You can specify the weight $w$ below.**
"""

METRIC_DEFINITION_INTRODUCTION = """
$\\text{Acc.}$: The accuracy of models trained on different samples.

$\\text{full-hard}$: Full dataset with hard labels.

$\\text{syn-hard}$: Synthetic dataset with hard labels.

$\\text{syn-any}$: Synthetic dataset with personalized evaluation methods (hard or soft labels).

$\\text{rdm-any}$: Randomly selected dataset (under the same compression ratio) with the same personalized evaluation methods.

$\\text{HLR} = \\text{Acc.} \\text{full-hard} - \\text{Acc.} \\text{syn-hard}$: The degree to which the original dataset is recovered under hard labels (hard label recovery).

$\\text{IOR} = \\text{Acc.} \\text{syn-any} - \\text{Acc.} \\text{rdm-any}$: The improvement over random selection when using personalized evaluation methods (improvement over random).
"""

DATASET_LIST = ["CIFAR-10", "CIFAR-100", "Tiny-ImageNet"]
IPC_LIST = ["IPC-1", "IPC-10", "IPC-50"]
DATASET_IPC_LIST = {
    "CIFAR-10": ["IPC-1", "IPC-10", "IPC-50"],
    "CIFAR-100": ["IPC-1", "IPC-10", "IPC-50"],
    "Tiny-ImageNet": ["IPC-1", "IPC-10"],
}
LABEL_TYPE_LIST = ["Hard Label", "Soft Label"]

METRICS = ["HLR", "IOR"]
METRICS_SIGN = [1.0, -1.0]
COLUMN_NAMES = ["Ranking", "Method", "Verified", "Date", "Label Type", "HLR%", "IOR%", "DDRS"]
DATA_TITLE_TYPE = ['number', 'markdown', 'markdown', 'markdown', 'markdown', 'number', 'number', 'number']

DATASET_MAPPING = {
    "CIFAR-10": 0,
    "CIFAR-100": 1,
    "Tiny-ImageNet": 2,
}

IPC_MAPPING = {
    "IPC-1": 0,
    "IPC-10": 1,
    "IPC-50": 2,
}

LABEL_MAPPING = {
    "Hard Label": 0,
    "Soft Label": 1,
}