Update app.py

app.py

@@ -4,10 +4,10 @@ from tensorflow.keras.applications.efficientnet import preprocess_input
 from tensorflow.keras.preprocessing import image
 import numpy as np
 
-# 🧠 Load model
+# Load trained model
 model = tf.keras.models.load_model("efficientnet_final_model.keras")
 
-# 🍃 Class names
+# Class labels
 CLASS_NAMES = [
     "Pomegranate__diseased", "mango_Sooty Mould", "mango_Powdery Mildew", 
     "mango_Healthy", "mango_Gall Midge", "mango_Die Back", 
@@ -18,25 +18,32 @@ CLASS_NAMES = [
     "lime_Scab", "lime_Anthracnose", "lime_Sooty Mould"
 ]
 
-# 🔍 Prediction function
+# Predict function
 def predict_disease(img):
+    print("🖼️ Image received")
     img = img.resize((160, 160))
     img_array = image.img_to_array(img)
     img_array = preprocess_input(img_array)
     img_array = np.expand_dims(img_array, axis=0)
+    
+    print(f"📊 Model input shape: {img_array.shape}")
     prediction = model.predict(img_array)[0]
+    print(f"🔮 Raw prediction: {prediction}")
+    
     top_idx = np.argmax(prediction)
     confidence = prediction[top_idx] * 100
     label = CLASS_NAMES[top_idx]
-    return f"{label} ({confidence:.2f}%)"
+    result = f"{label} ({confidence:.2f}%)"
+    print(f"✅ Final Result: {result}")
+    return result
 
-# 🎛️ Gradio interface
+# Gradio interface
 interface = gr.Interface(
     fn=predict_disease,
     inputs=gr.Image(type="pil"),
     outputs="text",
     title="🌿 Fruit Leaf Disease Classifier",
-    description="Upload a fruit or leaf image to identify the disease.",
+    description="Upload a fruit or leaf image to predict its disease type.",
     examples=[
         ["Phytopthora.jpg"],
         ["RedRust.jpg"]
@@ -45,5 +52,6 @@ interface = gr.Interface(
     allow_flagging="never"
 )
 
+# Launch with share link
 if __name__ == "__main__":
-    interface.launch()
+    interface.launch(share=True)