Training a model with getitune

getitune is a low-code transfer-learning library. Training is driven by an Engine created with create_engine(...), which pairs a model/recipe with a dataset and returns a runnable engine. Recipes (YAML under libraries/getitune/src/getitune/recipe/<task>/) bundle model + data pipeline + training config, so a model name alone gives a strong baseline.

There are two equal entry points that share the same objects and recipes:

• Python API — from getitune.engine import create_engine, then engine.train() / engine.test(). Preferred for notebooks, scripts, tests, and library integration. See libraries/getitune/README.md ("Quick Start") and the getitune documentation.
• CLI — getitune train --data_root <path> --model <name|recipe.yaml>. Preferred for reproducible experiments and shell workflows. See getitune train --help and the getitune documentation.