app.py

import cv2
import gradio as gr
import mediapipe as mp

mp_drawing = mp.solutions.drawing_utils
mp_drawing_styles = mp.solutions.drawing_styles
mp_hands = mp.solutions.hands

def fun(img):
    print(type(img))
    with mp_hands.Hands(
        model_complexity=0,
        min_detection_confidence=0.5,
        min_tracking_confidence=0.5
    ) as hands:
        img.flags.writeable = False
        image = cv2.flip(img[:, :, ::-1], 1)
        # Convert the BGR image to RGB before processing.
        results = hands.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
        image.flags.writeable = True
        if results.multi_hand_landmarks:
            for hand_landmarks in results.multi_hand_landmarks:
                mp_drawing.draw_landmarks(
                    image,
                    hand_landmarks,
                    mp_hands.HAND_CONNECTIONS,
                    mp_drawing_styles.get_default_hand_landmarks_style(),
                    mp_drawing_styles.get_default_hand_connections_style()
                )

        return cv2.flip(image[:, :, ::-1], 1)

with gr.Blocks(title="Realtime Keypoint Detection | Data Science Dojo", css="footer {display:none !important} .output-markdown{display:none !important}") as demo:
    with gr.Row():
        with gr.Column():
            webcam_input = gr.Video(label="Webcam Input", format="mp4")  # Webcam input

        with gr.Column():
            output = gr.Image(label="Output Image")

    webcam_input.stream(
        fn=fun,
        inputs=webcam_input,
        outputs=output
    )

demo.launch(debug=True)