Stevedore: a generic lightweight ML build setup in Docker
- Project
- 20219 IML4E
- Type
- Open Source Software
- Description
Wrapper class and generic API plus Podman/Docker build automation for Python ML models. A specific use case is a set of machine learning models that may be composed, so that they should be tested and packaged together. This by no means excludes use on single model. Available: https://github.com/reaktor/ml-py-stevedore
- Contact
- Johan Himberg
- johan.himberg@reaktor.com
- Research area(s)
- MLOps
- Technical features
Wrapper class and generic API plus Podman/Docker build automation for Python ML models. A specific use case is a set of machine learning models that may be composed, so that they should be tested and packaged together. This by no means excludes use on single model. Available: https://github.com/reaktor/ml-py-stevedore
- Integration constraints
HTTP-framework that serves the API is FastAPI. See details in https://github.com/reaktor/ml-py-stevedore
- Conditions for reuse
MIT license
- Confidentiality
- Public
- Publication date
- 01-09-2022
- Involved partners
- Reaktor Innovations (FIN)