Update app.py

app.py

@@ -3,16 +3,16 @@ import tensorflow as tf
 import numpy as np
 from PIL import Image
 
-# Load the trained Pap Smear model
+# Load your Pap Smear model
 model = tf.keras.models.load_model("papsmear-test_model.h5")
 
-# Threshold for classification
+# Optimal threshold
 THRESHOLD = 0.5
 
-# Preprocessing function (modify if your model used different preprocessing)
+# Preprocessing function
 def preprocess_image(img):
-    img = img.resize((224, 224))  # resize as per your model’s input size
-    img = np.array(img) / 255.0   # normalize
+    img = img.resize((224, 224))  # adjust if your model uses a different size
+    img = np.array(img) / 255.0
     img = np.expand_dims(img, axis=0)
     return img
 
@@ -23,12 +23,12 @@ def classify_image(image):
 
     if prediction > THRESHOLD:
         label = "🩸 Positive (Possible Abnormality Detected)"
-        confidence = f"Confidence: {prediction:.3f}"
+        confidence = prediction
     else:
         label = "✅ Negative (Normal Pap Smear)"
-        confidence = f"Confidence: {1 - prediction:.3f}"
+        confidence = 1 - prediction
 
-    return {label: float(prediction)} if prediction > THRESHOLD else {label: float(1 - prediction)}
+    return {label: float(confidence)}
 
 # Gradio Interface
 demo = gr.Interface(
@@ -37,10 +37,6 @@ demo = gr.Interface(
     outputs=gr.Label(num_top_classes=1, label="Classification Result"),
     title="Pap Smear Test Analyzer 🧫",
     description="Upload a Pap smear image to classify whether it is Normal (Negative) or Abnormal (Positive).",
-    examples=[
-        ["example_papsmear_normal.jpg"],
-        ["example_papsmear_positive.jpg"]
-    ]
 )
 
 if __name__ == "__main__":