Spaces:
Sleeping
Sleeping
import streamlit as st | |
import av | |
import joblib | |
import mediapipe as mp | |
import numpy as np | |
from streamlit_webrtc import webrtc_streamer, VideoTransformerBase | |
# Load trained model and label encoder | |
model = joblib.load("pose_classifier.joblib") | |
label_encoder = joblib.load("label_encoder.joblib") | |
# Initialize MediaPipe Pose | |
mp_pose = mp.solutions.pose | |
pose = mp_pose.Pose() | |
# Streamlit UI | |
st.title("Live Pose Classification on Hugging Face Spaces") | |
st.write("Using Streamlit WebRTC, OpenCV, and MediaPipe.") | |
class PoseClassification(VideoTransformerBase): | |
def transform(self, frame): | |
img = frame.to_ndarray(format="bgr24") | |
# Convert frame to RGB | |
img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) | |
# Process frame with MediaPipe Pose | |
results = pose.process(img_rgb) | |
if results.pose_landmarks: | |
landmarks = results.pose_landmarks.landmark | |
pose_data = [j.x for j in landmarks] + [j.y for j in landmarks] + \ | |
[j.z for j in landmarks] + [j.visibility for j in landmarks] | |
pose_data = np.array(pose_data).reshape(1, -1) | |
try: | |
y_pred = model.predict(pose_data) | |
predicted_label = label_encoder.inverse_transform(y_pred)[0] | |
# Draw label on frame | |
cv2.putText(img, f"Pose: {predicted_label}", (20, 50), | |
cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 3) | |
except Exception as e: | |
st.warning(f"⚠️ Prediction Error: {e}") | |
return av.VideoFrame.from_ndarray(img, format="bgr24") | |
# Start WebRTC streamer | |
webrtc_streamer(key="pose-classification", video_transformer_factory=PoseClassification) |