Update app.py

app.py

@@ -1,8 +1,7 @@
+import random
 import gradio as gr
 from PIL import Image
-import random
 from datasets import load_dataset
-
 from app.model import predict, gradcam, CLASS_NAMES
 
 # Load HF dataset once at startup
@@ -15,17 +14,15 @@ def to_pil(example):
     return Image.fromarray(example)
 
 def get_random_image():
-    """Return a random image from the HF dataset."""
     sample = random.choice(dataset)
-    img = sample["image"]  # dataset must have column "image"
-    return to_pil(img)
+    return to_pil(sample["image"])
 
 
 # Prediction and Grad-CAM logic
 def predict_fn(img):
     label, confidence, probs = predict(img)
     probs_sorted = {k: float(v) for k, v in sorted(probs.items(), key=lambda x: x[1], reverse=True)}
-    return {
+    return label, {
         "Predicted label": label,
         "Confidence": round(confidence, 3),
         "Class probabilities": probs_sorted
@@ -44,28 +41,27 @@ with gr.Blocks(title="Brain Tumor MRI Classifier (InceptionV3 + Grad-CAM)") as d
     with gr.Row():
         with gr.Column():
             input_img = gr.Image(type="pil", label="Upload MRI Image")
-
             random_btn = gr.Button("Use Random Dataset Image")
-
             interpolant_slider = gr.Slider(0, 1, value=0.5, label="Grad-CAM Intensity (interpolant)")
             submit_btn = gr.Button("Run Prediction + Grad-CAM")
 
         with gr.Column():
+            output_label = gr.Textbox(label="Predicted Label Only")
             output_json = gr.JSON(label="Prediction Results")
             output_cam = gr.Image(label="Grad-CAM Overlay")
 
-    # Button: Load random dataset image
+    # Load random image
     random_btn.click(
         fn=lambda: get_random_image(),
         inputs=[],
         outputs=[input_img]
     )
 
-    # Button: Run prediction
+    # Prediction + GradCAM
     submit_btn.click(
-        fn=lambda img, interp: (predict_fn(img), gradcam_fn(img, interp)),
+        fn=lambda img, interp: (*predict_fn(img), gradcam_fn(img, interp)),
         inputs=[input_img, interpolant_slider],
-        outputs=[output_json, output_cam]
+        outputs=[output_label, output_json, output_cam]
     )
 
 demo.launch()