moved gradcam inside app

app.py

@@ -1,7 +1,5 @@
 import gradio as gr
 import numpy as np
-from PIL import Image
-
 from app.predictor import predict_disease, compute_ai_risk
 from app.gradcam import generate_gradcam
 
@@ -13,10 +11,9 @@ def predict(image):
     # 2️⃣ GradCAM heatmap
     heatmap = generate_gradcam(tensor, original)
 
-    # 🔴 CRITICAL FIX → Convert heatmap to uint8 image
+    # Convert to displayable image
     if heatmap.max() <= 1:
         heatmap = heatmap * 255
-
     heatmap = heatmap.astype(np.uint8)
 
     # 3️⃣ Risk prediction
@@ -30,19 +27,27 @@ Confidence: {round(confidence*100,2)} %
 Risk Level: {risk}
 """
 
-    # 🔴 RETURN TEXT FIRST, IMAGE SECOND
     return report, heatmap
 
 
-demo = gr.Interface(
-    fn=predict,
-    inputs=gr.Image(type="pil", label="Upload Chest X-ray"),
-    outputs=[
-        gr.Textbox(label="AI Diagnosis Report"),
-        gr.Image(label="GradCAM Heatmap")
-    ],
-    title="CardioGuard AI",
-    description="Upload Chest X-ray to detect heart disease"
-)
+# 🔴 BLOCKS UI (no more Interface)
+with gr.Blocks(title="CardioGuard AI") as demo:
+
+    gr.Markdown("# 🫀 CardioGuard AI")
+    gr.Markdown("Upload Chest X-ray to detect heart disease")
+
+    with gr.Row():
+        image_input = gr.Image(type="pil", label="Upload X-ray")
+
+    run_btn = gr.Button("Analyze")
+
+    report_output = gr.Textbox(label="AI Diagnosis Report")
+    heatmap_output = gr.Image(label="GradCAM Heatmap")
+
+    run_btn.click(
+        fn=predict,
+        inputs=image_input,
+        outputs=[report_output, heatmap_output]
+    )
 
 demo.launch()