more clustering

Signed-off-by: James Ketrenos <james_git@ketrenos.com>

server/cluster.py

@@ -193,17 +193,36 @@ def update_face_identity(identities, face, closest):
 
 def cluster_faces(face):
   identities = []
+  perc = -1
   for i, face in enumerate(faces):
-    print(f'Clustering {i+1}/{len(faces)}')
+    new_perc = int(100 * (i+1) / len(faces))
+    if new_perc != perc:
+      perc = new_perc
+      print(f'Clustering faces {perc}% complete with {len(identities)} identities.')
     closest = find_nearest_face(faces, identities, face, threshold = 0.25)
     if closest == None:
-      print(f'Face {i+1} does not have any matches.')
       continue
     identity = update_face_identity(identities, face, closest)
 #    if identity['faces'] > 2:
 #     print(f'Updated identity {identity["id"]} to hold {identity["faces"]} faces.')
   return identities
 
+def cluster_identities(identities):
+  perc = -1
+  last_len = 0
+  while last_len != len(identities):
+    last_len = len(identities)
+    for i, identity in enumerate(identities):
+      new_perc = int(100 * (i+1) / len(identities))
+      if new_perc != perc:
+        perc = new_perc
+        print(f'Clustering identities {perc}% complete with {len(identities)} identities.')
+      closest = find_nearest_face([], identities, face, threshold = 0.25)
+      if closest == None:
+        continue
+      update_face_identity(identities, identity, closest)
+  return identities
+
 def identity_get_faces(item):
   return item['faces']
 
@@ -233,11 +252,14 @@ with conn:
     face['descriptors'] = np.frombuffer(descriptors)
 
   identities = cluster_faces(faces)
+  #identities = cluster_identities(identities)
   identities.sort(reverse = True, key = identity_get_faces)
+  sum = 0
   for identity in identities:
+    sum += identity['faces']
     print(f'{identity["id"]} has {identity["faces"]} faces')
 
-  print(f'{len(identities)} identities seeded.')
+  print(f'{len(identities)} identities seeded with {sum} faces.')
 
   exit(0)
   if False: