matrice-analytics 0.1.54__tar.gz → 0.1.56__tar.gz

{matrice_analytics-0.1.54 → matrice_analytics-0.1.56}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: matrice_analytics
-Version: 0.1.54
+Version: 0.1.56
 Summary: Common server utilities for Matrice.ai services
 Author-email: "Matrice.ai" <dipendra@matrice.ai>
 License-Expression: MIT

{matrice_analytics-0.1.54 → matrice_analytics-0.1.56}/matrice_analytics.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: matrice_analytics
-Version: 0.1.54
+Version: 0.1.56
 Summary: Common server utilities for Matrice.ai services
 Author-email: "Matrice.ai" <dipendra@matrice.ai>
 License-Expression: MIT

{matrice_analytics-0.1.54 → matrice_analytics-0.1.56}/src/matrice_analytics/post_processing/face_reg/embedding_manager.py

@@ -175,11 +175,14 @@ class EmbeddingManager:
         """Load all staff embeddings from API and cache them."""
         if not self.face_client:
             self.logger.error("Face client not available for loading staff embeddings")
+            print("ERROR: Face client not available for loading staff embeddings")
             return False
             
         try:
             self.logger.info("Loading staff embeddings from API...")
+            print("=============== LOADING STAFF EMBEDDINGS FROM API ===============")
             response = await self.face_client.get_all_staff_embeddings()
+            print(f"API RESPONSE TYPE: {type(response)}, IS_LIST: {isinstance(response, list)}, LEN: {len(response) if isinstance(response, list) else 'N/A'}")
             
             # Robust response handling: accept dict with data or raw list
             embeddings_data: List[Dict[str, Any]] = []
@@ -205,23 +208,58 @@ class EmbeddingManager:
             
             self.staff_embeddings = []
             embeddings_list = []
-            
+            expected_dim: Optional[int] = None
+            dims_observed: List[int] = []
+            mismatch_examples: List[Tuple[str, int]] = []  # (staffId, dim)
+
             for item in embeddings_data:
-                # if not item.get("isActive", True): # TODO: Check what is isActive
-                #     continue
-                    
+                # Skip inactive if provided
+                if isinstance(item, dict) and item.get("isActive") is False:
+                    continue
+
+                raw_emb = []
+                try:
+                    raw_emb = item.get("embedding", []) if isinstance(item, dict) else []
+                except Exception:
+                    raw_emb = []
+                # Record observed dimension for debugging
+                try:
+                    dims_observed.append(len(raw_emb) if isinstance(raw_emb, list) else 0)
+                except Exception:
+                    dims_observed.append(0)
+
+                # Validate and coerce embedding list
+                if not isinstance(raw_emb, list) or len(raw_emb) == 0:
+                    continue
+                try:
+                    # Ensure numeric float32 list
+                    clean_emb = [float(v) for v in raw_emb]
+                except Exception:
+                    continue
+
+                # Dimension consistency
+                if expected_dim is None:
+                    expected_dim = len(clean_emb)
+                if len(clean_emb) != expected_dim:
+                    # Collect a few examples to aid debugging
+                    try:
+                        mismatch_examples.append((str(item.get("staffId", "")), len(clean_emb)))
+                    except Exception:
+                        mismatch_examples.append(("", len(clean_emb)))
+                    self.logger.warning(f"Skipping embedding with mismatched dimension: got {len(clean_emb)} expected {expected_dim}")
+                    continue
+
                 staff_embedding = StaffEmbedding(
-                    embedding_id=item.get("embeddingId", ""),
-                    staff_id=item.get("staffId", ""),
-                    embedding=item.get("embedding", []),
-                    employee_id=str(item.get("employeeId", "")),
-                    staff_details=item.get("staffDetails", {}),
-                    is_active=item.get("isActive", True)
+                    embedding_id=(item.get("embeddingId", "") if isinstance(item, dict) else ""),
+                    staff_id=(item.get("staffId", "") if isinstance(item, dict) else ""),
+                    embedding=clean_emb,
+                    employee_id=str(item.get("employeeId", "")) if isinstance(item, dict) else "",
+                    staff_details=(item.get("staffDetails", {}) if isinstance(item, dict) else {}),
+                    is_active=(item.get("isActive", True) if isinstance(item, dict) else True)
                 )
-                
-                if staff_embedding.embedding:  # Only add if embedding exists
-                    self.staff_embeddings.append(staff_embedding)
-                    embeddings_list.append(staff_embedding.embedding)
+
+                self.staff_embeddings.append(staff_embedding)
+                embeddings_list.append(clean_emb)
             
             # Create numpy matrix for fast similarity computation (thread-safe)
             with self._embeddings_lock:
@@ -234,12 +272,31 @@ class EmbeddingManager:
                     
                     self.embedding_metadata = self.staff_embeddings.copy()
                     self.staff_embeddings_last_update = time.time()
-                    self.logger.info(f"Successfully loaded and cached {len(self.staff_embeddings)} staff embeddings")
-                    self.logger.debug(f"Embeddings matrix shape: {self.embeddings_matrix.shape}")
+                    self.logger.info(f"Successfully loaded and cached {len(self.staff_embeddings)} staff embeddings (dim={self.embeddings_matrix.shape[1]})")
+                    print(f"=============== SUCCESS: LOADED {len(self.staff_embeddings)} EMBEDDINGS, MATRIX SHAPE: {self.embeddings_matrix.shape} ===============")
+                    try:
+                        # Quick sanity metrics
+                        row0_sum = float(np.sum(self.embeddings_matrix[0])) if self.embeddings_matrix.shape[0] > 0 else 0.0
+                        row0_norm = float(np.linalg.norm(self.embeddings_matrix[0])) if self.embeddings_matrix.shape[0] > 0 else 0.0
+                        print(f"SANITY CHECK: row0_sum={row0_sum:.4f}, row0_norm={row0_norm:.4f} (should be ~1.0 after normalization)")
+                        self.logger.debug(f"Embeddings matrix shape: {self.embeddings_matrix.shape}, dtype={self.embeddings_matrix.dtype}, row0_sum={row0_sum:.4f}")
+                    except Exception as e:
+                        print(f"ERROR in sanity check: {e}")
                     return True
                 else:
-                    self.logger.warning("No active staff embeddings found in API response")
-                    return False
+                    # Build diagnostics and raise to stop pipeline early with actionable info
+                    dims_summary: Dict[int, int] = {}
+                    for d in dims_observed:
+                        dims_summary[d] = dims_summary.get(d, 0) + 1
+                    error_msg = (
+                        f"No valid staff embeddings loaded. Observed dimension distribution: {dims_summary}. "
+                        f"Expected_dim={expected_dim}. Mismatch examples (staffId, dim): {mismatch_examples[:5]}"
+                    )
+                    self.logger.error(error_msg)
+                    print(f"=============== ERROR: NO VALID EMBEDDINGS ===============")
+                    print(f"ERROR: {error_msg}")
+                    print(f"=============== STOPPING PIPELINE ===============")
+                    raise RuntimeError(f"Failed to load staff embeddings due to dimension mismatch. Observed dims: {dims_summary}")
                 
         except Exception as e:
             self.logger.error(f"Error loading staff embeddings: {e}", exc_info=True)
@@ -281,6 +338,7 @@ class EmbeddingManager:
         """Find best matching staff member using optimized matrix operations (thread-safe)."""
         with self._embeddings_lock:
             if self.embeddings_matrix is None or len(self.embedding_metadata) == 0:
+                print(f"ERROR: _find_best_local_match - embeddings_matrix is None={self.embeddings_matrix is None}, metadata_len={len(self.embedding_metadata)}")
                 return None
                 
             # Create local copies to avoid issues with concurrent modifications
@@ -292,6 +350,11 @@ class EmbeddingManager:
             
         try:
             query_array = np.array(query_embedding, dtype=np.float32).reshape(1, -1)
+            # Dimension check
+            if embeddings_matrix.shape[1] != query_array.shape[1]:
+                self.logger.warning(f"Query embedding dim mismatch: query={query_array.shape[1]} staff={embeddings_matrix.shape[1]}")
+                print(f"ERROR: DIMENSION MISMATCH - query={query_array.shape[1]} staff={embeddings_matrix.shape[1]}")
+                return None
             
             # Normalize query embedding
             query_norm = np.linalg.norm(query_array)
@@ -327,6 +390,9 @@ class EmbeddingManager:
             return 0.0
         try:
             query_array = np.array(query_embedding, dtype=np.float32).reshape(1, -1)
+            if embeddings_matrix.shape[1] != query_array.shape[1]:
+                print(f"ERROR: get_best_similarity DIMENSION MISMATCH - query={query_array.shape[1]} staff={embeddings_matrix.shape[1]}")
+                return 0.0
             qn = np.linalg.norm(query_array)
             if qn == 0:
                 return 0.0

{matrice_analytics-0.1.54 → matrice_analytics-0.1.56}/src/matrice_analytics/post_processing/face_reg/face_recognition.py

@@ -1603,11 +1603,11 @@ class FaceRecognitionEmbeddingUseCase(BaseProcessor):
         human_text_lines.append(f"\tRecognized: {face_summary.get('session_totals',{}).get('total_recognized', 0)}")  
         human_text_lines.append(f"\tUnknown: {face_summary.get('session_totals',{}).get('total_unknown', 0)}")
         # Additional counts similar to compare_similarity HUD
-        try:
-            human_text_lines.append(f"\tCurrent Faces (detections): {total_detections}")
-            human_text_lines.append(f"\tTotal Unique Tracks: {cumulative_total}")
-        except Exception:
-            pass
+        # try:
+        #     human_text_lines.append(f"\tCurrent Faces (detections): {total_detections}")
+        #     human_text_lines.append(f"\tTotal Unique Tracks: {cumulative_total}")
+        # except Exception:
+        #     pass
 
         human_text = "\n".join(human_text_lines)