Update app.py

app.py

@@ -3,7 +3,7 @@ from torchvision import models, transforms
 from PIL import Image
 import gradio as gr
 
-## Define the device
+# Define the device
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 # Load the trained model
@@ -27,7 +27,26 @@ transform = transforms.Compose([
     transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
 ])
 
-# Prediction function
+# Color mapping for labels
+label_colors = {
+    "Brown Spot": "#b2ff00",   
+    "Healthy": "#2ecc71",     
+    "Leaf Blast": "#ff00d4",   
+    "Neck Blast": "#ffd100"    
+}
+
+# Function to get color based on confidence
+def get_confidence_color(confidence):
+    if confidence < 0.25:
+        return "#e74c3c"  # Red
+    elif confidence < 0.50:
+        return "#f39c12"  
+    elif confidence < 0.75:
+        return "#00b9ff"  # Yellow
+    else:
+        return "#13ff00"  # Green
+
+# Updated Prediction Function
 def predict(image):
     # Ensure image is in RGB
     image = image.convert("RGB")
@@ -47,21 +66,27 @@ def predict(image):
     probabilities = torch.nn.functional.softmax(outputs, dim=1)[0]
     confidence = probabilities[predicted_class.item()].item()
     
-    return f"Predicted Disease: {predicted_label}\nConfidence: {confidence*100:.2f}%"
-
-# Load the model globally
-model = load_model()
+    # Generate styled output
+    label_color = label_colors.get(predicted_label, "#FFFFFF")  # Default White if not found
+    confidence_color = get_confidence_color(confidence)
+    
+    result = f"<div style='color:{label_color}; font-size:30px; font-weight:bold;'>{predicted_label}</div>"
+    result += f"<div style='color:{confidence_color}; font-size:25px; font-weight:bold;'>Confidence: {confidence*100:.2f}%</div>"
+    return result
 
-# Create Gradio interface
+# Updated Gradio Interface
 def launch_interface():
     # Create a Gradio interface
     iface = gr.Interface(
-        theme="Subh775/Green_valley",
+        theme=gr.themes.Citrus(
+            primary_hue="emerald",
+            neutral_hue="slate"
+        ),
         fn=predict,
         inputs=gr.Image(type="pil", label="Upload Rice Leaf Image"),
-        outputs=gr.Textbox(label="Prediction Results"),
-        title="Rice Disease Classification",
-        description="Upload a rice leaf image to detect it's condition (Brown Spot, Healthy, Leaf Blast or Neck blast)" ,
+        outputs=gr.HTML(label="Prediction Results"),
+        title="<span style='color: #00fff7; font-size:40px; font-weight: bold;'>Rice Disease Classification</span>",
+        description="<span style='color: lightblue; font-size:26px;'>Upload a rice leaf image to detect its condition (Brown Spot, Healthy, Leaf Blast, or Neck Blast)</span>",
         examples=[
             ["https://doa.gov.lk/wp-content/uploads/2020/06/brownspot3-1024x683.jpg"],
             ["https://arkansascrops.uada.edu/posts/crops/rice/images/Fig%206%20Rice%20leaf%20blast%20coalesced%20lesions.png"],
@@ -72,7 +97,10 @@ def launch_interface():
     
     return iface
 
+# Load the model globally
+model = load_model()
+
 # Launch the interface
 if __name__ == "__main__":
     interface = launch_interface()
-    interface.launch(share=True)
+    interface.launch(share=True)