Build the training folders for BirdNET-Analyzer

Copies the reviewed clips into the folder layout that the training script of BirdNET-Analyzer expects: one folder per class, named after the label (species_code, so the retrained classifier keeps the labels of the current one), with the negatives of a class in a folder with the same name prefixed by -. Clips of the sites in test_sites go to a separate test folder, to be passed as --test_data, so that the new classifier is evaluated on sites it was not trained on.

Usage

build_training_set(
  validation,
  output_dir,
  test_sites = NULL,
  negatives = TRUE,
  min_files = 100
)

Arguments

validation

Reviewed clips, as returned by classify_review(), post_validation() ($validation) or read_validation_tables(). It needs site, species_code, clip_file, verdict and reviewed_path (the path where the review left each clip).

output_dir

Output folder; train/ and, with test_sites, test/ are created in it.

test_sites

Sites held out for testing. NULL puts every clip in train/.

negatives

Copy the negative clips into -<species_code> folders.

min_files

Minimum number of positive training files per class below which a warning is raised.

Value

A tibble with one row per copied clip: site, species_code, verdict, set ("train" or "test"), class_folder, clip_file, source_audio, clip_start, clip_end, from and to, invisibly.

Details

The layout follows the documentation of BirdNET-Analyzer (version 2.4.0, birdnet_analyzer.train), which also recommends at least 100 files per species; classes below min_files in the training set raise a warning. Whole-recording clips of "random_recordings" (longer than 3 s, confidence = NA) are left out: their label says only that the species was heard somewhere in the recording.

The table of copied clips is also written to training_set.csv in output_dir; keep it with the classifier, to leave these clips out of later validation rounds with exclude_training_clips().