68f52818ae
* 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api * update job concurrency panel to show disabled queues formatting * check jobId in queueAll fix tests * remove outdated comment * better facial recognition icon * wording wording formatting * fixed tests * fix * formatting & sql * try to fix sql check * more detailed description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> |
||
|---|---|---|
| .. | ||
| ann | ||
| app | ||
| export | ||
| .dockerignore | ||
| .gitignore | ||
| Dockerfile | ||
| locustfile.py | ||
| log_conf.json | ||
| poetry.lock | ||
| pyproject.toml | ||
| README_es_ES.md | ||
| README_fr_FR.md | ||
| README.md | ||
| responses.json | ||
| start.sh | ||
Immich Machine Learning
- CLIP embeddings
- Facial recognition
Setup
This project uses Poetry, so be sure to install it first.
Running poetry install --no-root --with dev will install everything you need in an isolated virtual environment.
To add or remove dependencies, you can use the commands poetry add $PACKAGE_NAME and poetry remove $PACKAGE_NAME, respectively.
Be sure to commit the poetry.lock and pyproject.toml files to reflect any changes in dependencies.
Load Testing
To measure inference throughput and latency, you can use Locust using the provided locustfile.py.
Locust works by querying the model endpoints and aggregating their statistics, meaning the app must be deployed.
You can change the models or adjust options like score thresholds through the Locust UI.
To get started, you can simply run locust --web-host 127.0.0.1 and open localhost:8089 in a browser to access the UI. See the Locust documentation for more info on running Locust.
Note that in Locust's jargon, concurrency is measured in users, and each user runs one task at a time. To achieve a particular per-endpoint concurrency, multiply that number by the number of endpoints to be queried. For example, if there are 3 endpoints and you want each of them to receive 8 requests at a time, you should set the number of users to 24.