Update README.md

README.md

@@ -36,14 +36,7 @@ ___
 </a>
 </div>
 
-```python
-from Charm_tokenizer.ImageProcessor import Charm_Tokenizer
-
-img_path = r"img.png"
 
-charm_tokenizer = Charm_Tokenizer(patch_selection='frequency', training_dataset='tad66k', without_pad_or_dropping=True)
-tokens, pos_embed, mask_token = charm_tokenizer.preprocess(img_path)
-```
 Charm Tokenizer has the following input args:
 * patch_selection (str): The method for selecting important patches
   * Options: 'saliency', 'random', 'frequency', 'gradient', 'entropy', 'original'.
@@ -57,11 +50,29 @@ Charm Tokenizer has the following input args:
 * downscale_shortest_edge (int): Used for the 'original' patch selection strategy (default: 256).
 * without_pad_or_dropping (bool): Whether to avoid padding or dropping patches (default: True).
 
+**Note:** While random patch selection during training helps avoid overfitting,for consistent results during inference, fully deterministic patch selection approaches should be used. 
+
 The output is the preprocessed tokens, their corresponding positional embeddings, and a mask token that indicates which patches are in high resolution and which are in low resolution.
+
+```python
+from Charm_tokenizer.ImageProcessor import Charm_Tokenizer
+
+img_path = r"img.png"
+
+charm_tokenizer = Charm_Tokenizer(patch_selection='frequency', training_dataset='tad66k', without_pad_or_dropping=True)
+tokens, pos_embed, mask_token = charm_tokenizer.preprocess(img_path)
+```
 ___
 
 * Step 4) Predicting aesthetic/quality score
 
+  * If training_dataset is set to 'spaq' or 'koniq10k', the model predicts the image quality score. For other options ('aadb', 'tad66k', 'para', 'baid'), it predicts the image aesthetic score.
+
+  * Selecting a dataset with image resolutions similar to your input images can improve prediction accuracy.
+
+  * For more details about the process, please refer to the [paper](https://cvpr.thecvf.com/virtual/2025/poster/34423).
+
+
 ```python
 from Charm_tokenizer.Backbone import backbone
 
@@ -69,6 +80,4 @@ model = backbone(training_dataset='tad66k', device='cpu')
 prediction = model.predict(tokens, pos_embed, mask_token)
 ```
 
-**Note:**
-1. While random patch selection during training helps avoid overfitting,for consistent results during inference, fully deterministic patch selection approaches should be used. 
-2. For the training code, check our [GitHub Page](https://github.com/FBehrad/Charm/).
+**Note:** For the training code, check our [GitHub Page](https://github.com/FBehrad/Charm/).