immich-app/immich
1
0
Fork 0
mirror of https://github.com/immich-app/immich.git synced 2025-12-18 17:23:16 +03:00
Code Issues Packages Projects Releases 16 Wiki Activity

feat(ml)!: customizable ML settings (#3891)

Browse Source 
* consolidated endpoints, added live configuration

* added ml settings to server

* added settings dashboard

* updated deps, fixed typos

* simplified modelconfig

updated tests

* Added ml setting accordion for admin page

updated tests

* merge `clipText` and `clipVision`

* added face distance setting

clarified setting

* add clip mode in request, dropdown for face models

* polished ml settings

updated descriptions

* update clip field on error

* removed unused import

* add description for image classification threshold

* pin safetensors for arm wheel

updated poetry lock

* moved dto

* set model type only in ml repository

* revert form-data package install

use fetch instead of axios

* added slotted description with link

updated facial recognition description

clarified effect of disabling tasks

* validation before model load

* removed unnecessary getconfig call

* added migration

* updated api

updated api

updated api

---------

Co-authored-by: Alex Tran <alex.tran1502@gmail.com>
This commit is contained in:
Mert
2023-08-29 09:58:00 -04:00
committed by GitHub
parent 22f5e05060
commit bcc36d14a1
56 changed files with 2324 additions and 655 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
server/src/domain/smart-info/machine-learning.interface.ts
View File

@@ -1,9 +1,15 @@
import { ClassificationConfig, CLIPConfig, RecognitionConfig } from './dto';
export const IMachineLearningRepository = 'IMachineLearningRepository';
export interface MachineLearningInput {
export interface VisionModelInput {
imagePath: string;
}
export interface TextModelInput {
text: string;
}
export interface BoundingBox {
x1: number;
y1: number;
@@ -19,9 +25,20 @@ export interface DetectFaceResult {
embedding: number[];
}
export interface IMachineLearningRepository {
classifyImage(url: string, input: MachineLearningInput): Promise<string[]>;
encodeImage(url: string, input: MachineLearningInput): Promise<number[]>;
encodeText(url: string, input: string): Promise<number[]>;
detectFaces(url: string, input: MachineLearningInput): Promise<DetectFaceResult[]>;
export enum ModelType {
IMAGE_CLASSIFICATION = 'image-classification',
FACIAL_RECOGNITION = 'facial-recognition',
CLIP = 'clip',
}
export enum CLIPMode {
VISION = 'vision',
TEXT = 'text',
}
export interface IMachineLearningRepository {
classifyImage(url: string, input: VisionModelInput, config: ClassificationConfig): Promise<string[]>;
encodeImage(url: string, input: VisionModelInput, config: CLIPConfig): Promise<number[]>;
encodeText(url: string, input: TextModelInput, config: CLIPConfig): Promise<number[]>;
detectFaces(url: string, input: VisionModelInput, config: RecognitionConfig): Promise<DetectFaceResult[]>;
}