Update app.py

app.py

@@ -1,28 +1,42 @@
+import gradio as gr
 import tensorflow as tf
 import numpy as np
-from tensorflow.keras.preprocessing import image
-import gradio as gr
+import cv2
+
+# Load the SavedModel
+model = tf.keras.models.load_model("mask_mobilenet_savedmodel")  # Folder path
+
+# Prediction function
+def predict_mask(image):
+    try:
+        # Convert to RGB if needed
+        if image.shape[2] == 4:  # RGBA
+            image = cv2.cvtColor(image, cv2.COLOR_RGBA2RGB)
+
+        # Resize to model input
+        image = cv2.resize(image, (224, 224))
+        image = image / 255.0  # Normalize
+        image = np.expand_dims(image, axis=0)  # Add batch dimension
+
+        # Predict
+        preds = model.predict(image)
+        print("Preds:", preds)  # Logs in console
 
-# Load the SavedModel folder
-model = tf.keras.models.load_model("mask_mobilenet_savedmodel")
+        # Interpret prediction
+        result = "Mask" if preds[0][0] > 0.5 else "No Mask"
+        return result
 
-# Function to predict mask or no mask
-def predict_mask(img):
-    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"
+    except Exception as e:
+        print("Error:", e)  # Logs in console
+        return f"Error: {e}"
 
 # Gradio interface
 iface = gr.Interface(
     fn=predict_mask,
-    inputs=gr.Image(type="pil"),
-    outputs="text",
-    title="Mask Detection"
+    inputs=gr.Image(type="numpy"),
+    outputs=gr.Textbox(label="Prediction"),
+    title="Mask Detection",
+    description="Upload an image to check if a person is wearing a mask or not."
 )
 
 iface.launch()