SVLT

Serving Vision to Living Things.

Summary

SVLT is a service for on-demand computer vision, adapted specifically to image-based feedback in microscopy and other life sciences applications. It abstracts image data access, persists machine learning models, and exposes an extensible API to facilitate low-latency analysis.

Install Git and miniforge

1. Install Miniforge for environment management:
   https://github.com/conda-forge/miniforge/releases
2. Under the Start menu, open Miniforge3 > Miniforge Prompt

Install SVLT from source:

1. Install Git:
   https://git-scm.com/download/win
2. In the new terminal, clone the model_server repository:
   cd %userprofile%
git clone git@git.embl.de:grp-almf/svlt.git
3. Requirements depend on which SVLT packages to include. To create the target environment for svlt-pheno:
   mamba env create --file svlt-pheno/requirements.yml --name svlt-pheno-env
4. Activate the target environment: mamba activate svlt-pheno-env
5. Add the same packages from source in editable mode: pip install --no-deps -e ./svlt-core ./svlt-pheno

To start the server:

1. From the Miniforge prompt, run mamba activate svlt-pheno-env
2. Then run python -m scripts.run_server --port 6221
3. A browser window should appear, with basic status information.