Update app.py

app.py

@@ -1,38 +1,28 @@
-import gradio as gr
+import tensorflow as tf
 import numpy as np
-from tensorflow.keras.models import load_model
 from tensorflow.keras.preprocessing import image
-import tensorflow as tf
-import cv2
-
-# Load the model safely
-model = load_model("mask_mobilenet.h5", compile=False)
+import gradio as gr
 
-# Classes
-classes = ["Mask", "No Mask"]
+# Load the SavedModel folder
+model = tf.keras.models.load_model("mask_mobilenet_savedmodel")
 
+# Function to predict mask or no mask
 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
-
-    # 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}
+    img = img.resize((224, 224))
+    x = np.array(img) / 255.0
+    x = np.expand_dims(x, axis=0)
+    pred = model.predict(x)[0]
+    if pred[0] > pred[1]:
+        return "Mask"
+    else:
+        return "No Mask"
 
 # Gradio interface
 iface = gr.Interface(
     fn=predict_mask,
-    inputs=gr.Image(source="webcam", type="numpy"),
-    outputs=gr.Label(num_top_classes=2),
-    title="Mask Detection",
-    description="Upload an image or use webcam to detect face mask"
+    inputs=gr.Image(type="pil"),
+    outputs="text",
+    title="Mask Detection"
 )
 
-if __name__ == "__main__":
-    iface.launch()
+iface.launch()