auto_id: Automatic classification of sound events in recordings
In soundClass: Sound Classification Using Convolutional Neural Networks

auto_id

R Documentation

Automatic classification of sound events in recordings

Description

Run automatic classification of sound events on a set of recordings using a fitted model.

Usage

auto_id(model_path, update_progress = NA, metadata,
file_path, out_file, out_dir, save_png = TRUE, win_size = 50,
plot2console = FALSE, remove_noise = TRUE, recursive = FALSE, tx = 1)

Arguments

`model_path`	Character. Path to the fitted model.
`update_progress`	Progress bar only to be used inside shiny.
`metadata`	The object created with the function train_metadata() containing the parameters used to fit the model, or the path to the saved RDATA file.
`file_path`	Character. Path to the folder containing recordings to be classified by the fitted model.
`out_file`	Character. Name of the output file to save the results. Will be used to name the csv file and the sqlite database.
`out_dir`	Character. Path to the folder where the output results will be stored. Will be created if it doesn't exist already.
`save_png`	Logical. Should a spectrogram of the classified recordings with the identified event(s) and respective classification(s) be saved as png file?
`win_size`	Integer. Window size in ms to split recordings in chunks for classification. One peak per chunk is obtained and classified.
`plot2console`	Logical. Should a spectrogram of the classified recordings with the identified event(s) and respective classification(s) be plotted in the console while the analysis is running?
`remove_noise`	Logical. TRUE indicates that the model was fitted with a non-relevant class which will be deleted from the final output.
`recursive`	Logical. FALSE indicates that the recordings are in a single folder and TRUE indicates that there are recordings inside subfolders.
`tx`	Only used in recorders specifically intended for bat recordings. Can take the values "auto" or any numeric value. If the recording is not time expanded tx must be set to 1 (the default). If it's time expanded the numeric value corresponding to the time expansion should be indicated or "auto" should be selected. If tx = "auto" the function assumes that sampling rates < 50kHz corresponds to tx = 10 and > 50kHz to tx = 1.