Update app.py

app.py

@@ -1,34 +1,38 @@
 import gradio as gr
-import cv2
 import numpy as np
-import tensorflow as tf
 from tensorflow.keras.models import load_model
-from tensorflow.keras.applications.mobilenet_v2 import preprocess_input
-
-# Load model
-model = load_model("mask_mobilenet_fixed.h5", compile=False)
+from tensorflow.keras.preprocessing import image
+import tensorflow as tf
+import cv2
 
-IMG_SIZE = 224
+# Load the model safely
+model = load_model("mask_mobilenet.h5", compile=False)
 
-def predict_mask(image):
-    img = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
-    img = cv2.resize(img, (IMG_SIZE, IMG_SIZE))
-    img = preprocess_input(img)
-    img = np.expand_dims(img, axis=0)
+# Classes
+classes = ["Mask", "No Mask"]
 
-    prob = model.predict(img, verbose=0)[0][0]
+def predict_mask(img):
+    # Resize and preprocess the input image
+    img_resized = cv2.resize(img, (224, 224))
+    img_array = image.img_to_array(img_resized)
+    img_array = np.expand_dims(img_array, axis=0)  # shape (1, 224, 224, 3)
+    img_array = img_array / 255.0  # normalize
 
-    return {
-        "Mask 😷": float(1 - prob),
-        "No Mask ❌": float(prob)
-    }
+    # Make prediction
+    preds = model.predict(img_array)
+    class_idx = np.argmax(preds, axis=1)[0]
+    confidence = float(np.max(preds))
+    
+    return {classes[class_idx]: confidence}
 
+# Gradio interface
 iface = gr.Interface(
     fn=predict_mask,
-    inputs=gr.Image(type="numpy"),
+    inputs=gr.Image(source="webcam", type="numpy"),
     outputs=gr.Label(num_top_classes=2),
-    title="Face Mask Detection",
-    description="Upload an image to check whether a person is wearing a mask."
+    title="Mask Detection",
+    description="Upload an image or use webcam to detect face mask"
 )
 
-iface.launch()
+if __name__ == "__main__":
+    iface.launch()