Update app.py

app.py

@@ -1,6 +1,8 @@
 import gradio as gr
 import numpy as np
 import cv2
+import os
+import requests
 from tensorflow.keras.models import load_model
 from PIL import Image
 
@@ -16,9 +18,22 @@ CLASS_DESCRIPTIONS = {
     'Proliferative': 'Proliferative diabetic retinopathy. Advanced stage with new abnormal blood vessel growth.'
 }
 
+# --- 🔽 Ensure model is available locally ---
+MODEL_PATH = "diabetic_retinopathy_full_model.h5"
+MODEL_URL = "https://github.com/suhanii-23/retinopathy-detector/releases/download/v1.0-model/diabetic_retinopathy_full_model.h5"
+
+if not os.path.exists(MODEL_PATH):
+    print("Downloading model from GitHub release...")
+    r = requests.get(MODEL_URL, allow_redirects=True)
+    with open(MODEL_PATH, "wb") as f:
+        f.write(r.content)
+    print("✅ Model downloaded successfully!")
+
 # Load model
-model = load_model('diabetic_retinopathy_full_model.h5')
+model = load_model(MODEL_PATH)
+print("✅ Model loaded successfully!")
 
+# --- Image Preprocessing ---
 def crop_image_from_gray(img, tol=7):
     """Ben Graham's preprocessing: crop black borders"""
     if img.ndim == 2:
@@ -27,13 +42,13 @@ def crop_image_from_gray(img, tol=7):
     elif img.ndim == 3:
         gray_img = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
         mask = gray_img > tol
-        check_shape = img[:,:,0][np.ix_(mask.any(1), mask.any(0))].shape[0]
+        check_shape = img[:, :, 0][np.ix_(mask.any(1), mask.any(0))].shape[0]
         if check_shape == 0:
             return img
         else:
-            img1 = img[:,:,0][np.ix_(mask.any(1), mask.any(0))]
-            img2 = img[:,:,1][np.ix_(mask.any(1), mask.any(0))]
-            img3 = img[:,:,2][np.ix_(mask.any(1), mask.any(0))]
+            img1 = img[:, :, 0][np.ix_(mask.any(1), mask.any(0))]
+            img2 = img[:, :, 1][np.ix_(mask.any(1), mask.any(0))]
+            img3 = img[:, :, 2][np.ix_(mask.any(1), mask.any(0))]
             img = np.stack([img1, img2, img3], axis=-1)
         return img
 
@@ -45,11 +60,12 @@ def preprocess_image(image, sigmaX=10):
     image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
     image = crop_image_from_gray(image)
     image = cv2.resize(image, (IMAGE_WIDTH, IMAGE_HEIGHT))
-    image = cv2.addWeighted(image, 4, cv2.GaussianBlur(image, (0,0), sigmaX), -4, 128)
+    image = cv2.addWeighted(image, 4, cv2.GaussianBlur(image, (0, 0), sigmaX), -4, 128)
     image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
     
     return image
 
+# --- Prediction ---
 def predict_dr(image):
     """Main prediction function"""
     try:
@@ -60,11 +76,7 @@ def predict_dr(image):
         binary_pred = (predictions > 0.5).astype(int)
         final_class = binary_pred.sum(axis=1)[0] - 1
         
-        confidences = {
-            CLASSES[i]: float(predictions[0][i]) 
-            for i in range(len(CLASSES))
-        }
-        
+        confidences = {CLASSES[i]: float(predictions[0][i]) for i in range(len(CLASSES))}
         result_class = CLASSES[final_class]
         description = CLASS_DESCRIPTIONS[result_class]
         
@@ -77,9 +89,10 @@ def predict_dr(image):
     except Exception as e:
         return None, f"Error: {str(e)}", {}
 
+# --- Gradio UI ---
 with gr.Blocks(title="Diabetic Retinopathy Detector") as demo:
     gr.Markdown("""
-    # 🏥 Diabetic Retinopathy Detection
+    # 🏥 Diabetic Retinopathy Detection  
     Upload a retinal fundus image to detect diabetic retinopathy severity.
     
     **Classes:** Normal → Mild → Moderate → Severe → Proliferative
@@ -102,9 +115,9 @@ with gr.Blocks(title="Diabetic Retinopathy Detector") as demo:
     )
     
     gr.Markdown("""
-    ### ⚠️ Medical Disclaimer
+    ### ⚠️ Medical Disclaimer  
     This tool is for educational purposes only. Always consult a qualified healthcare provider.
     """)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()