Update app.py

app.py

@@ -1,75 +1,59 @@
 import streamlit as st
 import cv2
-import mediapipe as mp
 import numpy as np
-import tensorflow as tf
-from tensorflow.keras.models import load_model
-from PIL import Image
+from transformers import pipeline
 
-# Load the pre-trained model
 @st.cache_resource
-def load_stress_model():
-    return load_model("stress_model.h5")  # Replace with your actual model file
+def load_emotion_model():
+    # Load emotion recognition pipeline
+    return pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base")
 
-model = load_stress_model()
+# Load the model
+emotion_model = load_emotion_model()
 
-# Mediapipe face detection setup
-mp_face_mesh = mp.solutions.face_mesh
-face_mesh = mp_face_mesh.FaceMesh(min_detection_confidence=0.5, min_tracking_confidence=0.5)
-
-# Streamlit app UI
+# Streamlit UI
 st.title("Real-Time Stress Detection")
-st.write("This app detects stress levels in real-time using your webcam.")
-
-# Start webcam
-run_camera = st.button("Start Webcam")
-
-if run_camera:
-    st.write("Press 'q' to stop the camera.")
-    stframe = st.empty()  # Placeholder for video frames
+st.write("This app uses a Hugging Face emotion recognition model to estimate stress levels based on webcam input.")
 
-    cap = cv2.VideoCapture(0)  # Open webcam
+# Activate webcam
+run = st.checkbox("Run Webcam")
+frame_placeholder = st.empty()
 
-    while cap.isOpened():
+if run:
+    cap = cv2.VideoCapture(0)  # Start webcam
+    while True:
         ret, frame = cap.read()
         if not ret:
-            st.write("Failed to grab frame.")
+            st.error("Failed to access webcam.")
             break
 
-        # Flip and process the frame
-        frame = cv2.flip(frame, 1)
-        rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-        results = face_mesh.process(rgb_frame)
-
-        # Draw face mesh
-        if results.multi_face_landmarks:
-            for face_landmarks in results.multi_face_landmarks:
-                mp.solutions.drawing_utils.draw_landmarks(
-                    image=frame,
-                    landmark_list=face_landmarks,
-                    connections=mp_face_mesh.FACEMESH_TESSELATION,
-                    landmark_drawing_spec=None,
-                    connection_drawing_spec=mp.solutions.drawing_styles.get_default_face_mesh_tesselation_style()
-                )
-
-        # Resize for model prediction
-        img_resized = cv2.resize(rgb_frame, (224, 224)) / 255.0
-        img_resized = np.expand_dims(img_resized, axis=0)
-
-        # Model prediction
-        prediction = model.predict(img_resized)
-        stress_level = np.argmax(prediction)
-
-        # Display stress level
-        cv2.putText(frame, f"Stress Level: {stress_level}", (10, 30),
-                    cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2, cv2.LINE_AA)
-
-        # Stream to Streamlit
-        stframe.image(frame, channels="BGR")
-
-        # Break on 'q' key
-        if cv2.waitKey(1) & 0xFF == ord('q'):
+        # Process frame for display
+        frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+        frame_placeholder.image(frame_rgb, channels="RGB")
+
+        # Mock text-based emotion input for testing
+        # Replace this with input from a more suitable sensor or feature extractor
+        emotion_input = "I'm feeling anxious and stressed."
+
+        # Predict emotion
+        predictions = emotion_model(emotion_input)
+        predicted_emotion = predictions[0]["label"]
+        st.write(f"Predicted Emotion: {predicted_emotion}")
+
+        # Map emotion to stress level (example logic)
+        stress_mapping = {
+            "joy": "Low Stress",
+            "sadness": "High Stress",
+            "anger": "High Stress",
+            "fear": "High Stress",
+            "neutral": "Moderate Stress"
+        }
+        stress_level = stress_mapping.get(predicted_emotion, "Unknown")
+        st.write(f"Estimated Stress Level: {stress_level}")
+
+        # Break on user input
+        if st.button("Stop"):
             break
 
     cap.release()
-    cv2.destroyAllWindows()
+    st.write("Webcam stopped.")