Update app.py

app.py

@@ -6,10 +6,10 @@ from keras.models import load_model
 import cv2 as cv
 
 # Load the trained model
-model = load_model('FaceAuthenticator.keras')
+model = load_model('fake_real_face_classification_model.h5')
 
 # Load the pre-trained face detection model with error handling
-face_cascade = cv.CascadeClassifier('img_for_deepfake_detection\\hass_face.xml')
+face_cascade = cv.CascadeClassifier('hass_face.xml')
 
 # Define a function to preprocess the input image
 def preprocess_image(image_path):
@@ -21,59 +21,46 @@ def preprocess_image(image_path):
     return img_array
 
 # Define a function to classify the input image
-def classify_image(image_path):
-    # Preprocess the image
-    img_array = preprocess_image(image_path)
+def classify_image(image_data):
+    try:
+        # Save the uploaded image temporarily
+        temp_image_path = "temp_image.jpg"
+        image_data.save(temp_image_path)
 
-    # Convert the image to grayscale
-    gray_image = cv.cvtColor(cv.imread(image_path), cv.COLOR_BGR2GRAY)
+        # Preprocess the image
+        img_array = preprocess_image(temp_image_path)
 
-    # Detect faces in the image
-    faces = face_cascade.detectMultiScale(gray_image, scaleFactor=1.1, minNeighbors=5, minSize=(30, 30))
+        # Convert the image to grayscale
+        gray_image = cv.cvtColor(cv.imread(temp_image_path), cv.COLOR_BGR2GRAY)
 
-    # Check if any faces were detected
-    if len(faces) == 0:
-        return "No faces detected in the input image."
-    else:
-        # Make predictions
-        prediction = model.predict(img_array)
+        # Detect faces in the image
+        faces = face_cascade.detectMultiScale(gray_image, scaleFactor=1.1, minNeighbors=5, minSize=(30, 30))
 
-        # Return the prediction
-        if prediction[0][0] > 0.5:
-            return "The image is classified as real."
+        # Check if any faces were detected
+        if len(faces) == 0:
+            return "No faces detected in the input image."
         else:
-            return "The image is classified as fake."
+            # Make predictions
+            prediction = model.predict(img_array)
+
+            # Return the prediction
+            if prediction[0][0] > 0.5:
+                return "The image is classified as real."
+            else:
+                return "The image is classified as fake."
+    except Exception as e:
+        return f"An error occurred: {str(e)}"
 
 # Create the Gradio interface
 demo = gr.Interface(
     fn=classify_image,
-    inputs=gr.Image(type="file", label="Upload Image"),
+    inputs=gr.Image(type="pil", label="Upload Image"),
     outputs=gr.Textbox(label="Prediction"),
     title="DeepFake Image Detection",
     description="Upload an image and the model will classify it as real or fake.",
     theme="default",
-    layout="vertical",
-    css="""
-        .gradio-container {
-            font-family: 'Roboto', sans-serif;
-        }
-        .gradio-input, .gradio-output {
-            border: 1px solid #ccc;
-            border-radius: 4px;
-            padding: 10px;
-            font-size: 16px;
-        }
-        .gradio-button {
-            background-color: #4CAF50;
-            color: white;
-            border: none;
-            border-radius: 4px;
-            padding: 10px 20px;
-            font-size: 16px;
-            cursor: pointer;
-        }
-    """
+
 )
 
 # Launch the Gradio app
-demo.launch()
+demo.launch(share=True)