Alex The Bot cf4ec06750 Version v1.84.0 1 年間 前
..
app 87a0ba3db3 feat(ml): export clip models to ONNX and host models on Hugging Face (#4700) 1 年間 前
export 87a0ba3db3 feat(ml): export clip models to ONNX and host models on Hugging Face (#4700) 1 年間 前
.dockerignore 93863b0629 feat: facial recognition (#2180) 2 年 前
.gitignore 93863b0629 feat: facial recognition (#2180) 2 年 前
Dockerfile 87a0ba3db3 feat(ml): export clip models to ONNX and host models on Hugging Face (#4700) 1 年間 前
README.md cb437829f3 chore(docs): updated ML documentation (#4063) 1 年間 前
README_es_ES.md 1cf3378499 Add Spanish translations of Readme (#3511) 2 年 前
README_fr_FR.md b8777d7739 Add french documentation (#4010) 1 年間 前
locustfile.py 87a0ba3db3 feat(ml): export clip models to ONNX and host models on Hugging Face (#4700) 1 年間 前
log_conf.json 41461e0d5d chore(ml): memory optimisations (#3934) 1 年間 前
poetry.lock 87a0ba3db3 feat(ml): export clip models to ONNX and host models on Hugging Face (#4700) 1 年間 前
pyproject.toml cf4ec06750 Version v1.84.0 1 年間 前
responses.json 258b98c262 fix(ml): load models in separate threads (#4034) 1 年間 前
start.sh 0a24ff90bb fix(ml): set higher default worker timeout (#4007) 1 年間 前

README.md

Immich Machine Learning

  • Image classification
  • 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.