Update README.md

README.md

@@ -14,43 +14,45 @@ datasets:
 
 # EDSR-SR-DSC (4× Super-Resolution for Wind Data)
 
-This model is a custom-trained version of the Enhanced Deep Super-Resolution (EDSR) model from the `super-image` library. It is adapted for super-resolution of 2-channel weather data (e.g., wind u and v components), upscaling coarse-resolution wind fields by a factor of 4×.
+This model is a custom-trained version of the Enhanced Deep Super-Resolution (EDSR) model from the [`super-image`](https://github.com/eugenesiow/super-image) library.  
+It is adapted for super-resolution of **2-channel weather data** (e.g., wind u and v components), upscaling coarse-resolution wind fields by a factor of 4×.
 
+---
 
 ## 🧠 Model Architecture
 
 - **Base**: EDSR ([Lim et al. 2017](https://arxiv.org/abs/1707.02921))
-- **Input channels**: 2 
-- **Output channels**: 2
-- **Feature channels (`n_feats`)**: 64
-- **Residual blocks**: 32
-- **Upsampling**: Enabled
+- **Input channels**: 2  
+- **Output channels**: 2  
+- **Feature channels (`n_feats`)**: 64  
+- **Residual blocks**: 32  
+- **Mean-shift normalization**: Removed  
+- **Upsampling**: Enabled  
 - **Scale factor**: 4×
 
-
 ---
 
 ## 📦 Files in this Repository
 
 | File                   | Description                                   |
 |------------------------|-----------------------------------------------|
-| `config.json`          | Configuration compatible with `super-image`   |
-| `pytorch_model_4x.pt`  | Pretrained model weights (4× model)           |
+| `config.json`          | Configuration for the modified EDSR model     |
+| `pytorch_model_4x.pt`  | Pretrained weights for 4× upscaling           |
 
 ---
 
 ## 🚀 How to Use
 
 ```python
-from super_image import EdsrModel, ImageLoader
+from super_image import EdsrModel
 import torch
 
-# Load model
+# Load model and weights directly from Hugging Face Hub
 model = EdsrModel.from_pretrained("lschmidt/edsr-dsc", scale=4)
 
-# Load a 2-channel tensor (e.g., from a NetCDF or preprocessed image)
-# Example assumes shape (1, 2, H, W)
-inputs = torch.randn(1, 2, 64, 64)  # replace with your real data
+# Prepare input: must be a 4D tensor (B, C=2, H, W)
+inputs = torch.randn(1, 2, 64, 64)  # Replace with actual wind field data
 
-# Super-resolve
+# Forward pass
 outputs = model(inputs)
+