Update README.md

README.md

@@ -1,3 +1,11 @@
+---
+license: cc-by-nc-4.0
+language:
+- en
+tags:
+- superresolution
+- computervision
+---
 
 **DCASR**
 
@@ -5,15 +13,34 @@ The DCASR model, trained with the DIV2K dataset, is implemented using TensorFlow
 
 DCASR model has been proven to give better results than other SR models compared to other SR models. You can find all the details of the model in the source below.
 
-[A novel model for higher performance object detection with deep channel attention super resolution] https://doi.org/10.1016/j.jestch.2025.102003
+- <a href="https://doi.org/10.1016/j.jestch.2025.102003" target="_blank">A novel model for higher performance object detection with deep channel attention super resolution</a>
 
 *IMPORTANT: If you are going to use the DCASR model in your academic studies, you must cite the original article.*
 
 Model weights saved for x2, x3 and x4:
 
+- <a href="https://drive.google.com/file/d/1UL_tWB5Pht59ICLdnyxIjKa2BBd4EQ04/view?usp=sharing" target="_blank">DCASR_x2</a>
+- <a href="https://drive.google.com/file/d/1Hp94OjYxrXii1alYh5xMg3A7jW0AyOGn/view?usp=sharing" target="_blank">DCASR_x3</a>
+- <a href="https://drive.google.com/file/d/1DajIAnpvI1p1_ZRTny-gEDNKVaLuRPv0/view?usp=sharing" target="_blank">DCASR_x4</a>
+
 The model is built in tensorflow==2.14.0. 
 
 pip install tensorflow==2.14.0
 
 
 **Usage**
+```python
+  from tensorflow.keras.models import load_model
+  from PIL import Image
+  from skimage import io
+  import tensorflow as tf
+  
+  device = "/GPU:0" if tf.config.list_physical_devices('GPU') else "/CPU:0"
+  print(f"used device: {device}")
+  
+  model = load_model("DCASR_x2.keras")
+  original = io.imread("input/butterfly.png")
+  preds = model.predict_step(original)
+  preds_np = preds.numpy()
+  predicted_image = Image.fromarray(preds_np.astype('uint8'))
+  predicted_image.save("output/butterfly_x2.png")