quick add of default_{model|threshold} to settings, face_refimg_link now stores model_used and face_distance AND working implementation of own face_distance algorithm rather than compareAI(), removed older AI code it would no longer work with DB structures anyway, tweaked viewer to remove coords of unmatched faces for now

TODO

@@ -1,33 +1,24 @@
 ## GENERAL
 
-    * Face matching:
+    * allow for and implement: default_refimg_model and default_scan_model
-        - upgrade to face distance per face per file
+        - cnn for refimgs should be defaul, for scan use hog
-            - so we dont get 2 x same face in one file, and if it could match say Cam and Mich for 1 face, take the higher match, not the first one to be over the threshold
+        - research upsample val...
-        - allow for threshold/settings to be tweaked from the GUI?
-            ---> at least settings for default value (back to 0.6 / 0.5?)
-            ---> with override table to do per file / per face?
-        - face locations:
-            START FORM SCRATCH so all images have face_locn data
-        - algo:
-            for each face (even known) in image
-                foreach refimg
-                    get face_distance
-            sort by face_distance
-            for each face
-                connect lowest score with that face (for this file)
-                this means this face is no longer 'free' for a match
-                if (sorted) face distance > 0.55 stop as no further 'matches'
-        - use cnn model (check ftst.py) for ref images, and potentially as a setting to check images without a face?
-        - or always?
-            -- would CUDA be useful here? (which is faster say an old 730 or the AMD cpu?)
 
-    
+    * viewer needs to allow toggle to scan_model (and prob. right-click on file... AI (with CNN) AI (with hog)
+        - I think go to html5 toggles for: face, distance (only shows if you toggle face on), drop-down for model (allow change to cnn and reprocess)
+        - show matching face distance in viewer
+        - might be best for AI_Model to have friendly name (slow, slower) :)
+
+    * remove dirs after the duplicate cleanup removes all its content
+
+    * Face matching:
+        - upgrade to face distance per face per file [DONE]
+        - face locations:
+            START FORM SCRATCH for prod so all images have face_locn data
 
     * viewer:
         can we make it preload next/prev images, and only reload the image div when we jump?  to make arrow-based nav much faster
 
-    * remove dirs after the duplicate cleanup removes all its content
-
     * could look to remove the hand fixing of json.loads of array data --> seems you can make your own datatype in the ORM, and it can do the conversion every time you use it
         - https://stackoverflow.com/questions/28143557/sqlalchemy-convert-column-value-back-and-forth-between-internal-and-database-fo
 
@@ -52,22 +43,24 @@
     need a manual button to restart a job in the GUI, 
         (based on file-level optims, just run the job as new and it will optim over already done parts and continue)
 
-    Future:
-        Admin
-            -> reset face_flag
-
-        AI
-            -> rescan <dir> for <person> --> can do this on new image only
-            (optimised to only scan has_unidentified_face)... BUT if you change
-            thresholds on AI, or we get a new/better one some day, then it can
-            all images with faces, or if we 'reset face_flag' rescan all images
-
         Admin
             -> delete old jobs / auto delete jobs older than ???
             -> do I want to have admin roles/users?
 
+### AI
+    * faces per file (need a threshold for too many? OR
+    * consider size of bbox of face / 'high-quality' faces -- if face is too small in image, dont match it
+    * if we have a high-qual face, we could show this on a page and have UI to create ref img / person for it
+
 ### UI
     ??? ipads can't do selections and contextMenus, do I want to re-factor to cater for this?
+        - partial fix, double-click / tap allows viewing (most useful context-menu feature)
+
+    For AI / rescan:
+        way to override per file:
+            the model used
+            the threshold used?
+        maybe on the per file you could select an unknown face and add it as a ref img to a existing person, or make a new person and attach?
 
     file details is sort of crap - only works on import path
         - probably better to have a different 'view', e.g. folders/flat/detailed

pa_job_manager.py

@@ -190,9 +190,11 @@ class Settings(Base):
     import_path = Column(String)
     storage_path = Column(String)
     recycle_bin_path = Column(String)
+    default_model = Column(Integer,ForeignKey('ai_model.id'), unique=True, nullable=False)
+    default_threshold = Column(Integer)
 
     def __repr__(self):
-        return f"<id: {self.id}, import_path: {self.import_path}, recycle_bin_path: {self.recycle_bin_path}>"
+        return f"<id: {self.id}, import_path: {self.import_path}, recycle_bin_path: {self.recycle_bin_path}, default_model: {self.default_model}, default_threshold: {self.default_threshold}>"
         
 class PersonRefimgLink(Base):
     __tablename__ = "person_refimg_link"
@@ -459,8 +461,6 @@ def RunJob(job):
         JobMoveFiles(job)
     elif job.name == "restore_files":
         JobRestoreFiles(job)
-    elif job.name == "processai":
-        JobProcessAI(job)
     elif job.name == "run_ai_on":
         JobRunAIOn(job)
     elif job.name == "rotate_image":
@@ -959,26 +959,11 @@ def RunFuncOnFilesInPath( job, path, file_func, count_dirs ):
     return
 
 
-def JobProcessAI(job):
-    path=[jex.value for jex in job.extra if jex.name == "path"][0]
-    path_prefix=[jex.value for jex in job.extra if jex.name == "path_prefix"][0]
-    path = SymlinkName(path_prefix, path, '/')
-    p = session.query(Path).filter(Path.path_prefix==path).first()
-    job.num_files=p.num_files
-
-    RunFuncOnFilesInPath( job, path, ProcessAI, True )
-
-    FinishJob(job, "Finished Processesing AI")
-    return
-
 def WrapperForScanFileForPerson(job, entry):
-    which_person=[jex.value for jex in job.extra if jex.name == "person"][0]
-    
     if entry.type.name == 'Image':
         if DEBUG:
             AddLogForJob( job, f'INFO: processing File: {entry.name}' )
-        for pid in job.ppl:
+        ScanFileForPerson( job, entry, force=False)
-            ScanFileForPerson( job, entry, pid, force=False)
         # processed this file, add 1 to count
         job.current_file_num+=1
     return
@@ -992,9 +977,9 @@ def JobRunAIOn(job):
     AddLogForJob(job, f"INFO: Starting looking For faces in files job...")
     which_person=[jex.value for jex in job.extra if jex.name == "person"][0]
     if which_person == "all":
-        ppl=session.query(Person).all()
+        job.refimgs = session.query(Refimg).all()
     else:
-        ppl=session.query(Person).filter(Person.tag==which_person).all()
+        job.refimgs=session.query(Refimg).join(PersonRefimgLink).join(Person).filter(Person.tag==which_person).all()
 
     # start by working out how many images in this selection we will need face match on 
     job.num_files = 0
@@ -1011,13 +996,8 @@ def JobRunAIOn(job):
     job.current_file_num = 0
     session.commit()
 
-    ppl_lst=[]
-    for person in ppl:
-        ppl_lst.append(person.id)
-        
-    job.ppl = ppl_lst
-
     for jex in job.extra:
+        print( jex )
         if 'eid-' in jex.name:
             entry=session.query(Entry).get(jex.value)
             if entry.type.name == 'Directory':
@@ -1027,8 +1007,7 @@ def JobRunAIOn(job):
                 which_file=session.query(Entry).join(File).filter(Entry.id==jex.value).first()
                 if DEBUG:
                     AddLogForJob( job, f'INFO: processing File: {entry.name}' )
-                for person in ppl:
+                ScanFileForPerson( job, which_file, force=False)
-                    ScanFileForPerson( job, which_file, person.id, force=False)
                 # processed this file, add 1 to count
                 job.current_file_num+=1
             else:
@@ -1081,46 +1060,6 @@ def GenHashAndThumb(job, e):
     e.file_details.last_hash_date = time.time()
     return
 
-def ProcessAI(job, e):
-    if e.type.name != 'Image':
-        job.current_file_num+=1
-        return
-
-    file = e.FullPathOnFS()
-    stat = os.stat(file)
-    # find if file is newer than when we found faces before (fyi: first time faces_created_on == 0)
-    if stat.st_ctime > e.file_details.faces_created_on:
-        session.add(e)
-        im_orig = Image.open(file)
-        im = ImageOps.exif_transpose(im_orig)
-
-        faces = generateUnknownEncodings(im)
-        e.file_details.faces_created_on=time.time()
-        if faces:
-            flat_faces = numpy.array(faces)
-            e.file_details.faces = flat_faces.tobytes()
-        else:
-            e.file_details.faces = None
-            job.current_file_num+=1
-            return
-    else:
-        if not e.file_details.faces:
-            print("OPTIM: This image has no faces, skip it")
-            job.current_file_num+=1
-            return
-        recover=numpy.frombuffer(e.file_details.faces,dtype=numpy.float64)      
-        real_recover=numpy.reshape(recover,(-1,128))      
-        l=[]
-        for el in real_recover:
-            l.append(numpy.array(el))
-        faces = l
-    people = session.query(Person).all()
-    for unknown_encoding in faces:
-        for person in people:
-            lookForPersonInImage(job, person, unknown_encoding, e)
-    ProcessFileForJob(job, f"Finished processing {e.name}", e.name )
-    return
-
 def lookForPersonInImage(job, person, unknown_encoding, e):
     FinishJob( job, "THIS CODE HAS BEEN REMOVED, need to use new Face* tables, and rethink", "Failed" )
     return
@@ -1428,8 +1367,10 @@ def DelFacesForFile( eid ):
     session.commit()
     return
 
-def MatchRefimgToFace( refimg_id, face_id ):
+def MatchRefimgToFace( refimg_id, face_id, model, face_dist ):
-    rfl = FaceRefimgLink( refimg_id = refimg_id, face_id = face_id )
+    # remove any match to this face from previous attempts, and 'replace' with new one
+    session.query(FaceRefimgLink).filter(FaceRefimgLink.face_id==face_id).delete()
+    rfl = FaceRefimgLink( refimg_id = refimg_id, face_id = face_id, model_used=model, face_distance=face_dist )
     session.add(rfl)
     session.commit()
     return
@@ -1438,7 +1379,18 @@ def UnmatchedFacesForFile( eid ):
     rows = session.execute( f"select f.* from face f left join face_refimg_link frl on f.id = frl.face_id join face_file_link ffl on f.id = ffl.face_id where ffl.file_eid = {eid} and frl.refimg_id is null" )
     return rows
 
-def ScanFileForPerson( job, e, person_id, force=False ):
+def BestFaceMatch(dist, fid, threshold):
+    # 1 is not a match (0 is perfect match)
+    lowest=1.0
+    which=None
+    for who in dist:
+        if who in dist and fid in dist[who] and dist[who][fid][0] < lowest and dist[who][fid][0] <= threshold:
+            lowest=dist[who][fid][0]
+            which=who
+    print( f"bfm: return {which}, {lowest} for {fid}" )
+    return which, lowest
+
+def ScanFileForPerson( job, e, force=False ):
     file_h = session.query(File).get( e.id )
     # if we are forcing this, delete any old faces (this will also delete linked tables), and reset faces_created_on to None
     if force:
@@ -1446,12 +1398,12 @@ def ScanFileForPerson( job, e, person_id, force=False ):
         DelFacesForFile( e.id )
         file_h.faces_created_on = 0
 
-    # optimise: dont rescan if we already have faces (we are just going to try
+    # optimise: dont rescan if we already have faces 
-    # to match (maybe?) a refimg
     if file_h.faces_created_on == 0:
         if DEBUG:
             AddLogForJob( job, f"DEBUG: {e.name} is missing unknown faces, generating them" )
         im = face_recognition.load_image_file(e.FullPathOnFS())
+        # TODO: use setting to use model
         face_locations = face_recognition.face_locations(im)
         unknown_encodings = face_recognition.face_encodings(im, known_face_locations=face_locations)
         for locn, face in zip( face_locations, unknown_encodings ):
@@ -1459,22 +1411,35 @@ def ScanFileForPerson( job, e, person_id, force=False ):
         file_h.faces_created_on = time.time()
     session.commit()
 
-    ## now look for person
+    # get default_model from settings (test this)
-    refimgs = session.query(Refimg).join(PersonRefimgLink).filter(PersonRefimgLink.person_id==person_id).all()
+    settings = session.query(Settings).first()
-    uf = UnmatchedFacesForFile( e.id )
+    model=settings.default_model
-    if DEBUG and not uf:
+    threshold = settings.default_threshold
-        AddLogForJob( job, "DEBUG: {e.name} all faces already matched - finished" )
+
-        
+    faces = session.query(Face).join(FaceFileLink).filter(FaceFileLink.file_eid==e.id).all()
-    for face in uf:
+    # if there are no faces for this file, then dont go any futher
-        for r in refimgs:
+    if not faces:
+        return
+
+    dist={}
+    name={}
+    for r in job.refimgs:
+        dist[r.id]={}
+        name[r.id]=r.fname
+    for face in faces:
+        for r in job.refimgs:
             unknown_face_data = numpy.frombuffer(face.face, dtype=numpy.float64)
             refimg_face_data = numpy.frombuffer(r.face, dtype=numpy.float64)
-            match = compareAI(refimg_face_data, unknown_face_data)
+            dist[r.id][face.id] = face_recognition.face_distance(unknown_face_data, [refimg_face_data])
-            if match[0]:
+
-                AddLogForJob(job, f'WE MATCHED: {r.fname} with file: {e.name} ')
+    # if you need to check face distances, uncomment this: print( f"dist={dist}" )
-                MatchRefimgToFace( r.id, face.id )
+    faces = session.execute( f"select f.* from face f join face_file_link ffl on f.id = ffl.face_id where ffl.file_eid = {e.id}" )
-                # no need to keep looking for this face, we found it, go to next unknown face
+    for face in faces:
-                break
+        who, fd = BestFaceMatch(dist, face.id, threshold )
+        if who != None:
+            MatchRefimgToFace( who, face.id, model, fd )
+            AddLogForJob(job, f'WE MATCHED: {name[who]} with file: {e.name} - face distance of {fd}')
+            del( dist[who] )
     return
 
 
@@ -1482,7 +1447,7 @@ if __name__ == "__main__":
     print("INFO: PA job manager starting - listening on {}:{}".format( PA_JOB_MANAGER_HOST, PA_JOB_MANAGER_PORT) )
 
     InitialValidationChecks()
-    
+
     HandleJobs()
     with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
         s.bind((PA_JOB_MANAGER_HOST, PA_JOB_MANAGER_PORT))

settings.py

@@ -33,7 +33,7 @@ class Settings(db.Model):
     default_threshold = db.Column(db.Integer)
 
     def __repr__(self):
-        return f"<id: {self.id}, import_path: {self.import_path}, storage_path: {self.storage_path}, recycle_bin_path: {self.recycle_bin_path}>"
+        return f"<id: {self.id}, import_path: {self.import_path}, storage_path: {self.storage_path}, recycle_bin_path: {self.recycle_bin_path}, default_model: {self.default_model}, default_threshold: {self.default_threshold}>"
 
 ################################################################################
 # Helper class that inherits a .dump() method to turn class Settings into json / useful in jinja2

templates/viewer.html

@@ -73,6 +73,7 @@
                     context.fillStyle = "green"
                     context.fillText(faces[i].who, x+w/2, y-2)
                 }
+                /* can use to show lower left coords of a face for debugging
                 else
                 {
                     context.font = "14px Arial"
@@ -81,6 +82,7 @@
                     context.fillText( 'x=' + faces[i].x + ', y=' + faces[i].y, x+w/2, y-2)
                     context.fillText( 'x=' + faces[i].x + ', y=' + faces[i].y, x+w/2, y-2)
                 }
+                */
                 context.stroke();
             }
         }