Developer API

das.annot	Utilities for dealing with annotations.
das.augmentation	Waveform level augmentations.
das.block_stratify	A bit on semantics: - blocks are parts of the data (individual files in a file list, parts of a data array) - individual blocks are assigned specific groups (train/test/val)
das.evaluate
das.event_utils	Utilities for handling events.
das.loss	Backward-compatible custom losses.
das.make_dataset
das.models_legacy	Defines the network architectures.
das.npy_dir	Backward-compatible access to the NPY-directory storage API.
das.postprocessing
das.predict	Code for training and evaluating networks.
das.pulse_utils	Utilities for handling pulses.
das.segment_utils	Segment (syllable) utilities.
das.spec_utils	Backward-compatible spectrogram layers.
das.tracking	Utilities for logging training runs.
das.train	Code for training networks.
das.utils	General utilities
das.utils_plot	Plot utilities.
das.models	Model architectures, custom layers, and loading utilities.
das.models.architectures	Defines the network architectures.
das.models.loading	Model loading utilities.
das.models.menagerie	Utilities for interacting with DAS-Menagerie.
das.models.tcn(*args, **kwargs)	Synonym for tcn_stft.
das.models.tcn.tcn
das.models.tcn.tcn_new
das.models.kapre
das.models.kapre.augmentation	Legacy Kapre augmentation layers.
das.models.kapre.backend	Kapre backend functions Some backend functions that mainly use numpy. Functions with Keras' backend is in backend_keras.py.
das.models.kapre.backend_keras
das.models.kapre.filterbank
das.models.kapre.time_frequency
das.models.kapre.utils
das.io	I/O and dataset utilities for training and prediction.
das.io.data_hash
das.io.npy_dir	Dict of dicts <-> hierarchy of npy files.