immich/machine-learning
2024-01-08 05:19:11 +00:00
..
app fix(deps): update machine-learning (#5180) 2023-12-25 22:37:48 -05:00
export fix(deps): update machine-learning (#5180) 2023-12-25 22:37:48 -05:00
.dockerignore feat: facial recognition (#2180) 2023-05-17 12:07:17 -05:00
.gitignore feat: facial recognition (#2180) 2023-05-17 12:07:17 -05:00
Dockerfile fix(deps): update machine-learning (#5180) 2023-12-25 22:37:48 -05:00
locustfile.py feat(server,ml): remove image tagging (#5903) 2023-12-20 20:47:56 -05:00
log_conf.json feat(server,ml): remove image tagging (#5903) 2023-12-20 20:47:56 -05:00
poetry.lock fix(deps): update machine-learning (#5180) 2023-12-25 22:37:48 -05:00
pyproject.toml Version v1.92.0 2024-01-08 05:19:11 +00:00
README_es_ES.md Add Spanish translations of Readme (#3511) 2023-08-02 06:51:08 -05:00
README_fr_FR.md Add french documentation (#4010) 2023-09-08 13:48:39 +07:00
README.md feat(server,ml): remove image tagging (#5903) 2023-12-20 20:47:56 -05:00
responses.json fix(ml): load models in separate threads (#4034) 2023-09-09 16:02:44 +07:00
start.sh chore(ml): improve shutdown (#5689) 2023-12-14 13:51:24 -06:00

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.