Update code

Author: lizekai-richard

README.md

@@ -13,7 +13,7 @@
 Fair and benchmark for dataset distillation.
 </h3> -->
 <p align="center">
-| <a href=""><b>Documentation</b></a> | <a href=""><b>Leaderboard</b></a> | <b>Paper </b> (Coming Soon) | <a href=""><b>Twitter/X</b></a> | <a href=""><b>Developer Slack</b></a> |
+| <a href="https://nus-hpc-ai-lab.github.io/DD-Ranking/"><b>Documentation</b></a> | <a href="https://nus-hpc-ai-lab.github.io/DD-Ranking/"><b>Leaderboard</b></a> | <b>Paper </b> (Coming Soon) | <a href=""><b>Twitter/X</b></a> | <a href=""><b>Developer Slack</b></a> |
 </p>
 
 
@@ -43,9 +43,11 @@ Dataset Distillation (DD) aims to condense a large dataset into a much smaller o
 Notebaly, more and more methods are transitting from "hard label" to "soft label" in dataset distillation, especially during evaluation. **Hard labels** are categorical, having the same format of the real dataset. **Soft labels** are distributions, typically generated by a pre-trained teacher model. 
 Recently, Deng et al., pointed out that "a label is worth a thousand images". They showed analytically that soft labels are exetremely useful for accuracy improvement. 
 
-However, since the essence of soft labels is **knowledge distillation**, we want to ask a question: **Can the test accuracy of the model trained on distilled data reflect the real informativeness of the distilled data?**
+However, since the essence of soft labels is **knowledge distillation**, we find that when applying the same evaluation method to randomly selected data, the test accuracy also improves significantly (see the figure above).
 
-Specifically, we have discoverd unfairness of using only test accuracy to demonstrate one's performance from the following three aspects:
+This makes us wonder: **Can the test accuracy of the model trained on distilled data reflect the real informativeness of the distilled data?**
+
+Additionally, we have discoverd unfairness of using only test accuracy to demonstrate one's performance from the following three aspects:
 1. Results of using hard and soft labels are not directly comparable since soft labels introduce teacher knowledge.
 2. Strategies of using soft labels are diverse. For instance, different objective functions are used during evaluation, such as soft Cross-Entropy and Kullback–Leibler divergence. Also, one image may be mapped to one or multiple soft labels.
 3. Different data augmentations are used during evaluation.

dd_ranking/aug/__init__.py

@@ -1,4 +1,4 @@
-from .dsa import DSA_Augmentation
-from .mixup import Mixup_Augmentation
-from .cutmix import Cutmix_Augmentation
-from .zca import ZCA_Whitening_Augmentation
+from .dsa import DSAugmentation
+from .mixup import MixupAugmentation
+from .cutmix import CutmixAugmentation
+from .zca import ZCAWhiteningAugmentation

dd_ranking/aug/cutmix.py

@@ -3,7 +3,7 @@
 import kornia
 
 
-class Cutmix_Augmentation:
+class CutmixAugmentation:
     def __init__(self, params: dict):
         self.cutmix_p = params["cutmix_p"]
 

dd_ranking/aug/dsa.py

@@ -3,7 +3,7 @@
 import torch.nn.functional as F
 
 
-class DSA_Augmentation:
+class DSAugmentation:
 
     def __init__(self, params: dict, seed: int=-1, aug_mode: str='S'):        
         self.params = params

dd_ranking/aug/mixup.py

@@ -3,7 +3,7 @@
 import kornia
 
 
-class Mixup_Augmentation:
+class MixupAugmentation:
     def __init__(self, params: dict):
         self.mixup_p = params["mixup_p"]
 

dd_ranking/aug/zca.py

@@ -1,7 +1,7 @@
 import kornia
 
 
-class ZCA_Whitening_Augmentation:
+class ZCAWhiteningAugmentation:
     def __init__(self, params: dict):
         self.transform = kornia.enhance.ZCAWhitening()
 

dd_ranking/metrics/__init__.py

@@ -1,3 +1,3 @@
-from .general import Unified_Evaluator
-from .soft_label import Soft_Label_Evaluator
-from .hard_label import Hard_Label_Evaluator
+from .general import GeneralEvaluator
+from .soft_label import SoftLabelEvaluator
+from .hard_label import HardLabelEvaluator

dd_ranking/metrics/general.py

@@ -14,11 +14,11 @@
 from dd_ranking.utils import set_seed, get_optimizer, get_lr_scheduler
 from dd_ranking.utils import train_one_epoch, validate
 from dd_ranking.loss import SoftCrossEntropyLoss, KLDivergenceLoss
-from dd_ranking.aug import DSA_Augmentation, Mixup_Augmentation, Cutmix_Augmentation, ZCA_Whitening_Augmentation
+from dd_ranking.aug import DSAugmentation, MixupAugmentation, CutmixAugmentation, ZCAWhiteningAugmentation
 from dd_ranking.config import Config
 
 
-class Unified_Evaluator:
+class GeneralEvaluator:
 
     def __init__(self,
         config: Config=None,

dd_ranking/metrics/hard_label.py

@@ -16,7 +16,7 @@
 from dd_ranking.config import Config
 
 
-class Hard_Label_Evaluator:
+class HardLabelEvaluator:
 
     def __init__(self, config: Config=None, dataset: str='CIFAR10', real_data_path: str='./dataset/', ipc: int=10, 
                  model_name: str='ConvNet-3', data_aug_func: str='cutmix', aug_params: dict={'cutmix_p': 1.0}, optimizer: str='sgd', 

dd_ranking/metrics/soft_label.py

@@ -17,7 +17,7 @@
 from dd_ranking.config import Config
 
 
-class Soft_Label_Evaluator:
+class SoftLabelEvaluator:
 
     def __init__(self, config: Config=None, dataset: str='CIFAR10', real_data_path: str='./dataset/', ipc: int=10, model_name: str='ConvNet-3', 
                  soft_label_criterion: str='kl', data_aug_func: str='cutmix', aug_params: dict={'cutmix_p': 1.0}, soft_label_mode: str='S',