Update app.py

app.py

@@ -1,37 +1,35 @@
-import gradio as gr
+import streamlit as st
 import numpy as np
 from keras.models import load_model
 from keras.preprocessing import image
 from PIL import Image
+import os
 
-# Load model
+# Load the trained model
 model = load_model("Face Detector.keras")
 
-# Prediction function
-def predict_mask(img):
-    if img is None:
-        return "No image provided"
-    
-    img = img.resize((200, 200))
-    img_array = image.img_to_array(img)
-    img_array = np.expand_dims(img_array, axis=0)
-    img_array = img_array / 255.0
+st.title("😷 Face Mask Detection App")
+st.write("Upload an image and check if the person is wearing a mask.")
 
-    pred = model.predict(img_array)[0][0]
+# File uploader
+uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
 
-    if pred < 0.5:
-        return "✅ Mask is Detected"
-    else:
-        return "🚫 Mask is NOT Detected"
+if uploaded_file is not None:
+    # Show uploaded image
+    img = Image.open(uploaded_file)
+    st.image(img, caption="Uploaded Image", use_column_width=True)
 
-# Interface
-iface = gr.Interface(
-    fn=predict_mask,
-    inputs=gr.Image(source="webcam", tool="editor", type="pil"),
-    outputs="text",
-    title="😷 Face Mask Detection App",
-    description="Use your webcam or upload an image to check if a face mask is present."
-)
+    # Preprocess image
+    img = img.resize((200, 200))
+    img = image.img_to_array(img)
+    img = np.expand_dims(img, axis=0)
+    img = img / 255.0
 
-if __name__ == "__main__":
-    iface.launch()
+    # Predict
+    prediction = model.predict(img)[0][0]
+
+    # Result
+    if prediction < 0.5:
+        st.success("✅ Mask is Detected")
+    else:
+        st.error("🚫 Mask is NOT Detected")