.. _api: API Reference ============= .. automodule:: vak .. currentmodule:: vak This section documents the vak `API `_. Command Line Interface ---------------------- The :mod:`vak.cli` module implements the vak command line interface. .. autosummary:: :toctree: generated :template: module.rst cli.cli cli.eval cli.learncurve cli.predict cli.prep cli.train Commands -------- These high-level functions correspond to commands in the commmand-line interface. The commands are to prepare datasets, train and evaluate models, and generate predictions from trained models. Prep ~~~~ .. autosummary:: :toctree: generated :template: module.rst :recursive: prep prep.frame_classification prep.parametric_umap prep.spectrogram_dataset prep.unit_dataset prep.audio_dataset prep.constants prep.dataset_df_helper prep.prep_ prep.sequence_dataset Train-test-validation splits of datasets ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ The :mod:`vak.split` module contains functionality for generating train-validation-test splits from datasets. It is called by the :mod:`vak.prep` function when running ``vak prep`` through the command line interface. .. autosummary:: :toctree: generated :template: module.rst :recursive: prep.split.algorithms.bruteforce prep.split.algorithms.validate prep.split.split Train ~~~~~ .. autosummary:: :toctree: generated :template: module.rst :recursive: train.train_ train.frame_classification train.parametric_umap Eval ~~~~ .. autosummary:: :toctree: generated :template: module.rst :recursive: eval.eval_ eval.frame_classification eval.parametric_umap Predict ~~~~~~~ .. autosummary:: :toctree: generated :template: module.rst :recursive: predict.predict_ predict.frame_classification predict.parametric_umap Learning Curve ~~~~~~~~~~~~~~ .. autosummary:: :toctree: generated :template: module.rst :recursive: learncurve.curvefit learncurve.dirname learncurve.frame_classification learncurve.learncurve Configuration files ------------------- The :mod:`vak.config` module contains functions to parse the TOML configuration files used with vak, and dataclasses that represent tables from those files. .. autosummary:: :toctree: generated :template: module.rst :recursive: config.config config.dataset config.eval config.learncurve config.load config.model config.predict config.prep config.spect_params config.train config.trainer config.validators Datasets -------- The :mod:`vak.datasets` module contains datasets built into vak. .. autosummary:: :toctree: generated :template: module.rst :recursive: datasets.frame_classification datasets.parametric_umap Datapipes --------- The :mod:`vak.datapipes` module contains datapipes for loading dataset generated by :func:`vak.prep.prep`. .. autosummary:: :toctree: generated :template: module.rst :recursive: datapipes.frame_classification datapipes.parametric_umap Metrics ------- The :mod:`vak.metrics` module contains metrics used when evaluating neural network model performance. .. autosummary:: :toctree: generated :template: module.rst :recursive: metrics.classification.classification metrics.classification.functional metrics.distance.distance metrics.distance.functional Models ------- The :mod:`vak.models` module contains models built into vak, and functions for working with models: declaring them via definition, registering them as one of a family of models, getting a model instance for training, predicting, etc. .. autosummary:: :toctree: generated :template: module.rst :recursive: models.base models.convencoder_umap models.decorator models.definition models.ed_tcn models.frame_classification_model models.get models.parametric_umap_model models.registry models.tweetynet Nets ---- The :mod:`vak.nets` module contains neural network architectures built into vak. All models include a neural network architecture (along with an optimizer, loss function, and metrics). .. autosummary:: :toctree: generated :template: module.rst :recursive: nets.conv_encoder nets.ed_tcn nets.tweetynet Neural Network Layers and Operations ------------------------------------ The :mod:`vak.nn` module contains operations, layers, and other graph components used in neural network architectures. .. autosummary:: :toctree: generated :template: module.rst :recursive: nn.loss nn.functional Plotting -------- Functions for plotting that are built in to vak live in the :mod:`vak.plot` module. .. autosummary:: :toctree: generated :template: module.rst :recursive: plot.annot plot.learncurve plot.spect Transforms ---------- The :mod:`vak.transforms` module contains transforms that can be applied to input or output of neural networks, i.e., for pre-processing or post-processing. .. autosummary:: :toctree: generated :template: module.rst :recursive: transforms.defaults transforms.frame_labels.functional transforms.frame_labels.transforms transforms.functional transforms.transforms Common ------ This module contains helper functions used by multiple other modules. .. autosummary:: :toctree: generated :template: module.rst :recursive: common.accelerator common.annotation common.constants common.converters common.files common.labels common.learncurve common.logging common.paths common.tensorboard common.timebins common.timenow common.trainer common.typing common.validators