Update README.md

README.md

@@ -1,9 +1,9 @@
 ---
 license: mit
 tags:
-  - super-resolution
+  - downscaling
   - edsr
-  - weather
+  - ERA5 - COSMO-REA6
   - wind
   - super-image
 library_name: super-image
@@ -12,17 +12,17 @@ datasets:
   - your-dataset-name
 ---
 
-# EDSR-SR-DSC (4× Super-Resolution for Wind Data)
+# EDSR-DSC (4× Downscaling of Wind Velocities)
 
 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×.
+It is adapted for downscaling of **2-channel ERA5 data** (e.g., wind u and v components), by a factor of 4× (trained using **COSMO-REA6** as high-resolution data). 
 
 ---
 
 ## 🧠 Model Architecture
 
 - **Base**: EDSR ([Lim et al. 2017](https://arxiv.org/abs/1707.02921))
-- **Input channels**: 2  
+- **Input channels**: 2  (U & V components of wind speed)
 - **Output channels**: 2  
 - **Feature channels (`n_feats`)**: 64  
 - **Residual blocks**: 32  
@@ -51,7 +51,7 @@ import torch
 # load config 
 config, _ = EdsrConfig.from_pretrained("lschmidt/edsr-dsc")
 
-# load & modify model
+# load model & remove normalization
 model = EdsrModel(config)
 del model.sub_mean
 del model.add_mean
@@ -61,9 +61,9 @@ state_dict_path = hf_hub_download(repo_id="lschmidt/edsr-dsc", filename="pytorch
 state_dict = torch.load(state_dict_path, map_location="cpu")
 model.load_state_dict(state_dict, strict=False)
 
-# 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
+# sample input: must be a 4D tensor (B, C=2, H, W)
+inputs = torch.randn(1, 2, 64, 64)  # replace with coarse wind velocity fields
 
-# Forward pass
+# prediction
 outputs = model(inputs)