feat(server): separate face clustering job (#5598)

* separate facial clustering job

* update api

* fixed some tests

* invert clustering

* hdbscan

* update api

* remove commented code

* wip dbscan

* cleanup

removed cluster endpoint

remove commented code

* fixes

updated tests

minor fixes and formatting

fixed queuing

refinements

* scale search range based on library size

* defer non-core faces

* optimizations

removed unused query option

* assign faces individually for correctness

fixed unit tests

remove unused method

* don't select face embedding

update sql

linting

fixed ml typing

* updated job mock

* paginate people query

* select face embeddings because typeorm

* fix setting face detection concurrency

* update sql

formatting

linting

* simplify logic

remove unused imports

* more specific delete signature

* more accurate typing for face stubs

* add migration

formatting

* chore: better typing

* don't select embedding by default

remove unused import

* updated sql

* use normal try/catch

* stricter concurrency typing and enforcement

* update api

* update job concurrency panel to show disabled queues

formatting

* check jobId in queueAll

fix tests

* remove outdated comment

* better facial recognition icon

* wording

wording

formatting

* fixed tests

* fix

* formatting & sql

* try to fix sql check

* more detailed description

* update sql

* formatting

* wording

* update `minFaces` description

---------

Co-authored-by: Jason Rasmussen <jrasm91@gmail.com>
Co-authored-by: Alex Tran <alex.tran1502@gmail.com>
This commit is contained in:
Mert 2024-01-18 00:08:48 -05:00 committed by GitHub
parent 44873b4224
commit 68f52818ae
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
57 changed files with 1081 additions and 631 deletions

View file

@ -82,7 +82,7 @@
<SettingSelect
label="FACIAL RECOGNITION MODEL"
desc="Models are listed in descending order of size. Larger models are slower and use more memory, but produce better results. Note that you must re-run the Recognize Faces job for all images upon changing a model."
desc="Models are listed in descending order of size. Larger models are slower and use more memory, but produce better results. Note that you must re-run the Face Detection job for all images upon changing a model."
name="facial-recognition-model"
bind:value={config.machineLearning.facialRecognition.modelName}
options={[
@ -124,8 +124,8 @@
<SettingInputField
inputType={SettingInputFieldType.NUMBER}
label="MIN FACES DETECTED"
desc="The minimum number of faces of a person that must be detected for them to appear in the People tab. Setting this to a value greater than 1 can prevent strangers or blurry faces that are not the main subject of the image from being displayed."
label="MIN RECOGNIZED FACES"
desc="The minimum number of recognized faces for a person to be created. Increasing this makes Facial Recognition more precise at the cost of increasing the chance that a face is not assigned to a person."
bind:value={config.machineLearning.facialRecognition.minFaces}
step="1"
min="1"