Update app.py

app.py

@@ -31,7 +31,7 @@ index_to_class = {
 
 inv_index_to_class = {v: k for k, v in index_to_class.items()}
 
-
+webcam = cv2.VideoCapture(0)
 
 # Preprocess landmarks
 def preprocess_landmarks(hand1_landmarks, hand2_landmarks, pose_landmarks, lip_landmarks):
@@ -72,15 +72,43 @@ def extract_landmarks(frame):
 
 # Make prediction
 def make_prediction(processed_landmarks):
-    #inputs = np.array([processed_landmarks])
-    #interpreter.set_tensor(input_details[0]['index'], inputs)
-    #interpreter.invoke()
-    #index = outputs[0].argmax()
-    print(processed_landmarks)
-    return print(processed_landmarks) #index_to_class[index]
+    inputs = np.array([processed_landmarks])
+    interpreter.set_tensor(input_details[0]['index'], inputs)
+    interpreter.invoke()
+    index = outputs[0].argmax()
+    return index_to_class[index]
 
 # Gradio Interface Function
 def predict_with_webcam(frame):
+
+    # Initialize webcam capture (the default camera, usually index 0)
+    webcam = cv2.VideoCapture(0)
+
+    while True:
+        # Capture a frame from the webcam
+        ret, frame = webcam.read()
+
+        if not ret:
+            print("Failed to capture frame from the webcam.")
+            break
+
+        landmarks = extract_landmarks(frame)
+        if landmarks is not None:
+            processed_landmarks = preprocess_landmarks(*landmarks)
+            prediction = make_prediction(processed_landmarks)
+            print("Prediction:", prediction)
+
+        # Display the frame in a window (optional)
+        cv2.imshow("Webcam", frame)
+
+        # Break the loop when the user presses the 'q' key
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    # Release the webcam and close the window
+    webcam.release()
+    cv2.destroyAllWindows()
+    
     landmarks = extract_landmarks(frame)
     if landmarks is not None:
         processed_landmarks = preprocess_landmarks(*landmarks)