.

app.py

@@ -4,11 +4,14 @@ import json
 import tensorflow_hub as hub
 from PIL import Image
 
+# Ensure KerasLayer is recognized when loading the model
 tf.keras.utils.get_custom_objects().update({'KerasLayer': hub.KerasLayer})
 
+# Paths to your model and label files
 class_file_path = './labels.json'
 model_file_path = './model.h5'
 
+# Load the model
 model = tf.keras.models.load_model(model_file_path)
 
 def load_breeds(file_path=class_file_path):
@@ -17,14 +20,14 @@ def load_breeds(file_path=class_file_path):
 
 labels = load_breeds()
 
-# Disease list as one space-separated string (title case, spaces not underscores)
-disease_list_str = " ".join([label.replace(' ', '_').title() for label in labels])
+# Format disease list as comma-separated string, nice readable format
+disease_list_str = ", ".join([label.replace('_', ' ').title() for label in labels])
 
-# Example organic treatments per disease (fill with your actual treatments)
+# Organic treatments dictionary with keys matching formatted labels exactly
 organic_treatments = {
     "Maize Rust": "Use neem oil spray weekly and rotate crops to prevent rust spread.",
     "Maize Fall Armyworm": "Introduce natural predators like Trichogramma wasps and use Bacillus thuringiensis (Bt) sprays.",
-    "Maize Grasshoper": "Manual removal and natural bird repellents recommended.",
+    "Maize Grasshopper": "Manual removal and natural bird repellents recommended.",
     "Maize Healthy": "No treatment needed. Maintain good crop hygiene.",
     "Maize Leaf Beetle": "Apply insecticidal soap and promote beneficial insects like ladybugs.",
     "Maize Leaf Blight": "Use resistant varieties and apply copper-based fungicides organically.",
@@ -37,8 +40,8 @@ organic_treatments = {
     "Tomato Septoria Leaf Spot": "Mulch soil and use biofungicides such as Bacillus subtilis.",
     "Tomato Spider Mites Two Spotted Spider Mite": "Introduce predatory mites and spray insecticidal soap.",
     "Tomato Target Spot": "Crop rotation and neem oil sprays are effective.",
-    "Tomato Tomato YellowLeaf Curl Virus": "Control whitefly vectors and use resistant varieties.",
-    "Tomato Tomato Mosaic Virus": "Remove infected plants and sanitize tools regularly.",
+    "Tomato Yellowleaf Curl Virus": "Control whitefly vectors and use resistant varieties.",
+    "Tomato Mosaic Virus": "Remove infected plants and sanitize tools regularly.",
     "Tomato Healthy": "No treatment needed. Keep plants healthy with regular watering and nutrients."
 }
 
@@ -58,22 +61,28 @@ def predict_breed(image):
         predictions = model.predict(img_array)[0]
         top3_indices = predictions.argsort()[-3:][::-1]
 
-        top_pred_class = labels[top3_indices[0]]
-        if "maize" not in top_pred_class.lower() and "tomato" not in top_pred_class.lower():
+        top_pred_class_raw = labels[top3_indices[0]]
+        top_pred_class = top_pred_class_raw.replace('_', ' ').title()
+
+        # Check for valid crops
+        if "Maize" not in top_pred_class and "Tomato" not in top_pred_class:
             return "❌ This model only supports Maize and Tomato leaf images.", {}, ""
 
+        # Build prediction text with markdown formatting
         output_lines = ["🌿 **Top 3 Predictions:**"]
         confidence_scores = {}
 
         for i in top3_indices:
             class_name = labels[i].replace('_', ' ').title()
             confidence = predictions[i] * 100
-            output_lines.append(f"{class_name}: {confidence:.2f}%")
+            output_lines.append(f"- **{class_name}**: {confidence:.2f}%")
             confidence_scores[class_name] = float(f"{confidence:.2f}")
 
-        treatment = organic_treatments.get(top_pred_class.replace('_', ' ').title(), "No organic treatment available.")
+        treatment = organic_treatments.get(top_pred_class, "No organic treatment available.")
+
+        treatment_text = f"🌱 **Organic Treatment for {top_pred_class}:**\n\n{treatment}"
 
-        return "\n".join(output_lines), confidence_scores, f"🌱 **Organic Treatment for {top_pred_class.replace('_', ' ').title()}:**\n{treatment}"
+        return "\n".join(output_lines), confidence_scores, treatment_text
 
     except Exception as e:
         print("Prediction Error:", e)
@@ -81,13 +90,12 @@ def predict_breed(image):
 
 with gr.Blocks() as demo:
     gr.Markdown("# 🌿 Hares: Maize & Tomato Disease Classifier")
-    gr.Markdown("## Supported Diseases:")
-    gr.Markdown(disease_list_str)
-    
+    gr.Markdown(f"### Supported Diseases:\n\n{disease_list_str}")
+
     image_input = gr.Image(type="pil", label="Upload Maize or Tomato Leaf Image")
-    prediction_text = gr.Text(label="Prediction")
-    confidence_bar = gr.Label(label="Confidence Scores")
-    treatment_text = gr.Textbox(label="Organic Treatment", lines=4)
+    prediction_text = gr.Markdown(label="Prediction")
+    confidence_bar = gr.JSON(label="Confidence Scores")
+    treatment_text = gr.Markdown(label="Organic Treatment")
 
     image_input.change(fn=predict_breed, inputs=image_input, outputs=[prediction_text, confidence_bar, treatment_text])