Update app.py

app.py

@@ -9,10 +9,10 @@ model.fc = torch.nn.Linear(model.fc.in_features, 2)
 model.load_state_dict(torch.load("skin_cancer_resnet18_version1.pt", map_location="cpu"))
 model.eval()
 
-# Classes
+# Class labels
 classes = ['benign', 'malignant']
 
-# Preprocessing
+# Image preprocessing
 transform = transforms.Compose([
     transforms.Resize((224, 224)),
     transforms.ToTensor()
@@ -27,13 +27,21 @@ def predict(img):
         probs = torch.nn.functional.softmax(output[0], dim=0)
     return {classes[i]: float(probs[i]) for i in range(2)}
 
-# Interface
+# UI text
+title = "🧠 Lumen: Skin Cancer Classifier"
+description = """
+Upload a dermoscopic image of a mole or skin lesion.<br>
+The model will classify it as <b>benign</b> or <b>malignant</b> based on its appearance.<br><br>
+<b>Disclaimer:</b> This tool is for research and educational use only. It is not a diagnostic device.
+"""
+
+# Gradio Interface
 demo = gr.Interface(
     fn=predict,
-    inputs=gr.Image(type="pil", label="Upload a skin lesion image"),
-    outputs=gr.Label(num_top_classes=2),
-    title="Skin Cancer Classifier",
-    description="Upload a dermoscopic image of a mole or lesion to get a prediction (benign vs malignant)."
+    inputs=gr.Image(type="pil", label="Upload Lesion Image"),
+    outputs=gr.Label(num_top_classes=2, label="Prediction"),
+    title=title,
+    description=description
 )
 
 demo.launch()