config.rst

Preset Configurations

This module contains preset configurations for baseline CNN architectures and datamodules.

Models

Preset Datamodules

Datamodules include iterative accessors to raw data (:ref:`ptbench.setup.databases`) including data pre-processing to a minimum input standard, if applicable. Use these datamodules for training and evaluating your models.

Remix Datamodules

We provide some aggregated datamodules to facilitate cross-database development.

Cross-validation Datamodules

We support cross-validation with precise preset folds. In this section, you will find the configuration for the first fold (fold-0) for all supported datamodules. Nine other folds are available for every configuration (from 1 to 9), making up 10 folds per supported datamodule.