matrice-analytics 0.1.46__tar.gz → 0.1.47__tar.gz

{matrice_analytics-0.1.46 → matrice_analytics-0.1.47}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: matrice_analytics
-Version: 0.1.46
+Version: 0.1.47
 Summary: Common server utilities for Matrice.ai services
 Author-email: "Matrice.ai" <dipendra@matrice.ai>
 License-Expression: MIT

{matrice_analytics-0.1.46 → matrice_analytics-0.1.47}/matrice_analytics.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: matrice_analytics
-Version: 0.1.46
+Version: 0.1.47
 Summary: Common server utilities for Matrice.ai services
 Author-email: "Matrice.ai" <dipendra@matrice.ai>
 License-Expression: MIT

{matrice_analytics-0.1.46 → matrice_analytics-0.1.47}/src/matrice_analytics/post_processing/face_reg/face_recognition.py

@@ -883,7 +883,7 @@ class FaceRecognitionEmbeddingUseCase(BaseProcessor):
         """Process face recognition for each detection with embeddings"""
 
         # Initialize face client only when needed and if credentials are available
-        st=time.time()
+        st0=time.time()
         if not self.face_client:
             try:
                 self.face_client = self._get_facial_recognition_client(config)
@@ -894,7 +894,7 @@ class FaceRecognitionEmbeddingUseCase(BaseProcessor):
                 # No client available, return empty list (no results)
                 return []
         print("------------------FACE RECOG CLIENT INIT----------------------------")
-        print("LATENCY:",(time.time() - st)*1000,"| Throughput fps:",(1.0 / (time.time() - st)) if (time.time() - st) > 0 else None)
+        print("LATENCY:",(time.time() - st0)*1000,"| Throughput fps:",(1.0 / (time.time() - st0)) if (time.time() - st0) > 0 else None)
         print("------------------FACE RECOG CLIENT INIT----------------------------")
 
         # Initialize unknown faces storage if not exists
@@ -938,14 +938,14 @@ class FaceRecognitionEmbeddingUseCase(BaseProcessor):
         for detection in detections:
             
             # Process each detection sequentially with await to preserve order
-            st=time.time()
+            st1=time.time()
             processed_detection = await self._process_face(
                 detection, current_frame, location, current_timestamp, config,
                 current_recognized_count, current_unknown_count, 
                 recognized_persons, current_frame_staff_details
             )
             print("------------------WHOLE FACE RECOG PROCESSING DETECTION----------------------------")
-            print("LATENCY:",(time.time() - st)*1000,"| Throughput fps:",(1.0 / (time.time() - st)) if (time.time() - st) > 0 else None)
+            print("LATENCY:",(time.time() - st1)*1000,"| Throughput fps:",(1.0 / (time.time() - st1)) if (time.time() - st1) > 0 else None)
             print("------------------FACE RECOG PROCESSING DETECTION----------------------------")
 
             # Include both known and unknown faces in final detections (maintains original order)
@@ -977,7 +977,7 @@ class FaceRecognitionEmbeddingUseCase(BaseProcessor):
     ) -> Dict:
 
         # Extract and validate embedding using EmbeddingManager
-        st=time.time()
+        st2=time.time()
         detection, embedding = self.embedding_manager.extract_embedding_from_detection(detection)
         if not embedding:
             return None
@@ -985,7 +985,7 @@ class FaceRecognitionEmbeddingUseCase(BaseProcessor):
         # Internal tracker-provided ID (from AdvancedTracker; ignore upstream IDs entirely)
         track_id = detection.get("track_id")
         print("------------------FACE RECOG EMBEDDING EXTRACTION----------------------------")
-        print("LATENCY:",(time.time() - st)*1000,"| Throughput fps:",(1.0 / (time.time() - st)) if (time.time() - st) > 0 else None)
+        print("LATENCY:",(time.time() - st2)*1000,"| Throughput fps:",(1.0 / (time.time() - st2)) if (time.time() - st2) > 0 else None)
         print("------------------FACE RECOG EMBEDDING EXTRACTION----------------------------")
 
         # Determine if detection is eligible for recognition (similar to compare_similarity gating)
@@ -1049,7 +1049,7 @@ class FaceRecognitionEmbeddingUseCase(BaseProcessor):
                         except Exception:
                             pass
                 else: #if eligible for recognition
-                    st=time.time()
+                    st3=time.time()
                     staff_id, person_name, similarity_score, employee_id, staff_details, detection_type = await self.temporal_identity_manager.update(
                         track_id=track_key,
                         emb=embedding,
@@ -1058,7 +1058,7 @@ class FaceRecognitionEmbeddingUseCase(BaseProcessor):
                         timestamp=current_timestamp,
                     )
                     print("------------------FACE RECOG TEMPORAL IDENTITY MANAGER UPDATE----------------------------")
-                    print("LATENCY:",(time.time() - st)*1000,"| Throughput fps:",(1.0 / (time.time() - st)) if (time.time() - st) > 0 else None)
+                    print("LATENCY:",(time.time() - st3)*1000,"| Throughput fps:",(1.0 / (time.time() - st3)) if (time.time() - st3) > 0 else None)
                     print("------------------FACE RECOG TEMPORAL IDENTITY MANAGER UPDATE----------------------------")
         except Exception as e:
             self.logger.warning(f"TemporalIdentityManager update failed: {e}")
@@ -1133,21 +1133,21 @@ class FaceRecognitionEmbeddingUseCase(BaseProcessor):
                 and employee_id
                 and not str(employee_id).startswith("unknown_")
             ):
-                st=time.time()
+                st4=time.time()
                 await self.people_activity_logging.enqueue_detection(
                     detection=detection,
                     current_frame=current_frame,
                     location=location,
                 )
                 print("------------------FACE RECOG ENQUEUEING DETECTION FOR ACTIVITY LOGGING----------------------------")
-                print("LATENCY:",(time.time() - st)*1000,"| Throughput fps:",(1.0 / (time.time() - st)) if (time.time() - st) > 0 else None)
+                print("LATENCY:",(time.time() - st4)*1000,"| Throughput fps:",(1.0 / (time.time() - st4)) if (time.time() - st4) > 0 else None)
                 print("------------------FACE RECOG ENQUEUEING DETECTION FOR ACTIVITY LOGGING----------------------------")
 
                 self.logger.debug(f"Enqueued known face detection for activity logging: {detection.get('person_name', 'Unknown')}")
         except Exception as e:
             self.logger.error(f"Error enqueueing detection for activity logging: {e}")
         print("------------------FACE RECOG ENQUEUEING DETECTION FOR ACTIVITY LOGGING----------------------------")
-        print("LATENCY:",(time.time() - st)*1000,"| Throughput fps:",(1.0 / (time.time() - st)) if (time.time() - st) > 0 else None)
+        print("LATENCY:",(time.time() - st2)*1000,"| Throughput fps:",(1.0 / (time.time() - st2)) if (time.time() - st2) > 0 else None)
         print("------------------FACE RECOG ENQUEUEING DETECTION FOR ACTIVITY LOGGING----------------------------")
 
         return detection