matrice-analytics 0.1.46__tar.gz → 0.1.48__tar.gz

{matrice_analytics-0.1.46 → matrice_analytics-0.1.48}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: matrice_analytics
-Version: 0.1.46
+Version: 0.1.48
 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-0.1.48}/matrice_analytics.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: matrice_analytics
-Version: 0.1.46
+Version: 0.1.48
 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-0.1.48}/src/matrice_analytics/post_processing/face_reg/face_recognition.py

@@ -126,6 +126,7 @@ class TemporalIdentityManager:
         if not emb or not isinstance(emb, list):
             return None, "Unknown", 0.0, None, {}, "unknown"
         try:
+            st10=time.time()
             resp = await self.face_client.search_similar_faces(
                 face_embedding=emb,
                 threshold=0.01,  # low threshold to always get top-1
@@ -134,6 +135,10 @@ class TemporalIdentityManager:
                 location=location,
                 timestamp=timestamp,
             )
+            print("------------------FACE RECOG TEMPORAL IDENTITY MANAGER UPDATE - COMPUTE BEST IDENTITY----------------------------")
+            print("LATENCY:",(time.time() - st10)*1000,"| Throughput fps:",(1.0 / (time.time() - st10)) if (time.time() - st10) > 0 else None)
+            print("------------------FACE RECOG TEMPORAL IDENTITY MANAGER UPDATE - COMPUTE BEST IDENTITY----------------------------")
+
         except Exception as e:
             self.logger.error(f"API ERROR: Failed to search similar faces in _compute_best_identity: {e}", exc_info=True)
             return None, "Unknown", 0.0, None, {}, "unknown"
@@ -226,11 +231,19 @@ class TemporalIdentityManager:
         stable_employee_id = s.get("stable_employee_id")
         stable_score = float(s.get("stable_score", 0.0))
         stable_staff_details = s.get("stable_staff_details", {}) if isinstance(s.get("stable_staff_details"), dict) else {}
+        st7=time.time()
+        print("------------------FACE RECOG TEMPORAL IDENTITY MANAGER UPDATE - STABLE VALUES----------------------------")
+        print("LATENCY:",(time.time() - st7)*1000,"| Throughput fps:",(1.0 / (time.time() - st7)) if (time.time() - st7) > 0 else None)
+        print("------------------FACE RECOG TEMPORAL IDENTITY MANAGER UPDATE - STABLE VALUES----------------------------")
 
         if eligible_for_recognition and emb:
+            st8=time.time()
             staff_id, person_name, inst_score, employee_id, staff_details, det_type = await self._compute_best_identity(
                 emb, location=location, timestamp=timestamp
             )
+            print("------------------FACE RECOG TEMPORAL IDENTITY MANAGER UPDATE - COMPUTE BEST IDENTITY----------------------------")
+            print("LATENCY:",(time.time() - st8)*1000,"| Throughput fps:",(1.0 / (time.time() - st8)) if (time.time() - st8) > 0 else None)
+            print("------------------FACE RECOG TEMPORAL IDENTITY MANAGER UPDATE - COMPUTE BEST IDENTITY----------------------------")
 
             is_inst_known = staff_id is not None and inst_score >= self.threshold
             if is_inst_known:
@@ -290,7 +303,12 @@ class TemporalIdentityManager:
                 return stable_staff_id, stable_person_name or "Unknown", float(inst_score), stable_employee_id, stable_staff_details, "known"
 
             # Fallback: use prototype from history
+            st9=time.time()
             fb_staff_id, fb_name, fb_score, fb_employee_id, fb_details, fb_type = await self._compute_best_identity_from_history(s, location=location, timestamp=timestamp)
+            print("------------------FACE RECOG TEMPORAL IDENTITY MANAGER UPDATE - COMPUTE BEST IDENTITY FROM HISTORY----------------------------")
+            print("LATENCY:",(time.time() - st9)*1000,"| Throughput fps:",(1.0 / (time.time() - st9)) if (time.time() - st9) > 0 else None)
+            print("------------------FACE RECOG TEMPORAL IDENTITY MANAGER UPDATE - COMPUTE BEST IDENTITY FROM HISTORY----------------------------")
+
             if fb_staff_id is not None and fb_score >= max(0.0, self.threshold - self.fallback_margin):
                 s["label_votes"][fb_staff_id] += 1  # type: ignore
                 s["stable_staff_id"] = fb_staff_id
@@ -883,7 +901,7 @@ 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 +912,7 @@ 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 +956,14 @@ 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 +995,7 @@ 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 +1003,7 @@ 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 +1067,7 @@ 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 +1076,7 @@ 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 +1151,21 @@ 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

{matrice_analytics-0.1.46 → matrice_analytics-0.1.48}/src/matrice_analytics/post_processing/face_reg/face_recognition_client.py

@@ -447,7 +447,7 @@ class FacialRecognitionClient:
             )
             
             embeddings_count = 0
-            if response.get('success', False):
+            if response: #.get('success', False):
                 data = response.get('data', [])
                 embeddings_count = len(data) if isinstance(data, list) else 0
                 self.logger.info(f"API RESPONSE: Retrieved {embeddings_count} staff embeddings")