Create app.py

app.py

@@ -0,0 +1,115 @@
+import streamlit as st
+import cv2
+import mediapipe as mp
+import numpy as np
+import pickle
+import torch
+import time
+import pandas as pd
+
+# Load ML model
+model = pickle.load(open('model.pkl', 'rb'))
+
+# Load YOLOv7 model (GPU or CPU)
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+yolo_model = torch.hub.load('WongKinYiu/yolov7', 'custom', 'yolov7.pt', source='local').to(device)
+
+# Mediapipe setup
+mp_face = mp.solutions.face_detection.FaceDetection(model_selection=0, min_detection_confidence=0.5)
+mp_hands = mp.solutions.hands.Hands()
+mp_pose = mp.solutions.face_mesh.FaceMesh()
+
+# Streamlit UI setup
+st.set_page_config(page_title="Multi-Face Attention Detector", layout='wide')
+st.title("🎥 Real-Time Multi-Face Attention Detector (YOLOv7 + Mediapipe + GPU)")
+run = st.checkbox('Start Webcam')
+
+FRAME_WINDOW = st.image([])
+attention_log = []
+start_time = time.time()
+
+if run:
+    cap = cv2.VideoCapture(0)
+    while cap.isOpened():
+        ret, frame = cap.read()
+        if not ret:
+            st.warning("⚠️ Cannot access webcam.")
+            break
+
+        h, w, _ = frame.shape
+
+        # YOLOv7 phone detection
+        results = yolo_model([frame])
+        phones = []
+        for det in results.xyxy[0]:
+            cls_id = int(det[-1])
+            if cls_id == 67:  # COCO class: cellphone
+                phones.append((int(det[0]), int(det[1]), int(det[2] - det[0]), int(det[3] - det[1])))
+
+        # Mediapipe face detection
+        face_res = mp_face.process(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
+        if face_res.detections:
+            for i, det in enumerate(face_res.detections):
+                bbox = det.location_data.relative_bounding_box
+                face_x, face_y = int(bbox.xmin * w), int(bbox.ymin * h)
+                face_w, face_h = int(bbox.width * w), int(bbox.height * h)
+                face_conf = det.score[0]
+
+                # Hand tracking
+                hand_res = mp_hands.process(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
+                no_hands = len(hand_res.multi_hand_landmarks) if hand_res.multi_hand_landmarks else 0
+
+                # Head pose (simplified)
+                pose_res = mp_pose.process(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
+                pose_label, pose_x, pose_y = 'forward', 0, 0
+                if pose_res.multi_face_landmarks:
+                    nose = pose_res.multi_face_landmarks[0].landmark[1]
+                    pose_x, pose_y = int(nose.x * w), int(nose.y * h)
+                    if pose_y > h * 0.6: pose_label = 'down'
+                    elif pose_x < w * 0.3: pose_label = 'left'
+                    elif pose_x > w * 0.7: pose_label = 'right'
+                pose_map = {'forward': 0, 'down': 1, 'left': 2, 'right': 3}
+                pose_code = pose_map.get(pose_label, 0)
+
+                phone_detected = int(any(
+                    face_x < p[0] + p[2] < face_x + face_w and face_y < p[1] + p[3] < face_y + face_h
+                    for p in phones
+                ))
+
+                if phones:
+                    phone_x, phone_y, phone_w, phone_h = phones[0]
+                else:
+                    phone_x, phone_y, phone_w, phone_h = 0, 0, 0, 0
+
+                feature_vector = np.array([[1, face_x, face_y, face_w, face_h, face_conf,
+                                            no_hands, pose_code, pose_x, pose_y, phone_detected,
+                                            phone_x, phone_y, phone_w, phone_h, 0.8]])
+
+                pred = model.predict(feature_vector)[0]
+                attention_text = 'Attentive' if pred == 0 else 'Inattentive'
+
+                attention_log.append({'face_id': i + 1, 'time': time.time() - start_time, 'state': attention_text})
+
+                color = (0, 255, 0) if pred == 0 else (0, 0, 255)
+                cv2.rectangle(frame, (face_x, face_y), (face_x + face_w, face_y + face_h), color, 2)
+                cv2.putText(frame, f'Face {i + 1}: {attention_text}', (face_x, face_y - 10),
+                            cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 2)
+
+        FRAME_WINDOW.image(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+
+# Process log for dashboard
+if attention_log:
+    df = pd.DataFrame(attention_log)
+    attentive = df[df['state'] == 'Attentive'].shape[0]
+    inattentive = df[df['state'] == 'Inattentive'].shape[0]
+    st.markdown("### 📊 Attention Statistics")
+    st.write(f"✅ Attentive detections: {attentive}")
+    st.write(f"⚠️ Inattentive detections: {inattentive}")
+    st.dataframe(df.tail(10))
+    st.line_chart(df.groupby('time')['state'].apply(lambda x: (x == 'Attentive').mean()))
+    st.download_button("Download Log as CSV", df.to_csv(index=False), file_name="attention_log.csv")