Update app.py

app.py

@@ -1,44 +1,35 @@
+import gradio as gr
+import math
 import cv2
-import mediapipe as mp
 import numpy as np
-import streamlit as st
+import mediapipe as mp
 
-# Initialize MediaPipe Pose
+# Initialize mediapipe pose class
 mp_pose = mp.solutions.pose
-pose = mp_pose.Pose(static_image_mode=False, model_complexity=1, enable_segmentation=False, min_detection_confidence=0.5)
+pose = mp_pose.Pose(static_image_mode=False, min_detection_confidence=0.5, model_complexity=1)
 mp_drawing = mp.solutions.drawing_utils
 
-# Streamlit web interface
-st.title("Yoga Pose Detector")
-st.text("Using Mediapipe and Streamlit")
-
-run = st.checkbox('Run')
-FRAME_WINDOW = st.image([])
-
-cap = cv2.VideoCapture(0)
-
-while run:
-    ret, frame = cap.read()
-    if not ret:
-        st.error("Failed to capture image from webcam")
-        break
-
-    # Convert the BGR image to RGB
-    image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-
-    # Process the image and detect pose
-    results = pose.process(image)
-
-    # Draw pose landmarks
-    if results.pose_landmarks:
-        mp_drawing.draw_landmarks(image, results.pose_landmarks, mp_pose.POSE_CONNECTIONS)
-
-    # Convert the image color back for OpenCV
-    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
-
-    # Display the image in the web interface
-    FRAME_WINDOW.image(image)
-
-cap.release()
-cv2.destroyAllWindows()
-
+def detectPose(image):
+    # Your detectPose function implementation
+    pass
+
+def classifyPose(landmarks, image):
+    # Your classifyPose function implementation
+    pass
+
+def detect_yoga_poses(frame):
+    frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+    frame, landmarks = detectPose(frame)
+    if landmarks:
+        frame, _ = classifyPose(landmarks, frame)
+    return frame
+
+iface = gr.Interface(
+    fn=detect_yoga_poses,
+    inputs="webcam",
+    outputs="image",
+    title="Live Yoga Pose Detection",
+    description="This app detects yoga poses from the live camera feed using MediaPipe.",
+)
+
+iface.launch()