ertk.preprocessing.keras_apps.KerasAppsExtractorConfig

class ertk.preprocessing.keras_apps.KerasAppsExtractorConfig(model: str = '???', size: int | None = None, n_mels: int = 128, spec_type: str = 'mel', fmax: int = 8000)

Bases: ERTKConfig

Configuration for KerasAppsExtractor.

__init__(model: str = '???', size: int | None = None, n_mels: int = 128, spec_type: str = 'mel', fmax: int = 8000) → None

Methods

__init__([model, size, n_mels, spec_type, fmax])

Inherited Methods

`default`()	Create default config.
`from_config`(config)	Create config object from any compatible config.
`from_file`(path)	Create config from YAML file and optionlly override some values.
`merge_with_args`(args)	Merge config with command-line arguments.
`merge_with_config`(config)	Merge other config into this config.
`to_dictconfig`()	Convert config to DictConfig.
`to_file`(path)	Write config to YAML file.
`to_string`()	Generate YAML string representation of config.

Attributes

`fmax`	Maximum frequency for spectrogram extraction.
`model`	Name of the model to use.
`n_mels`	Number of mel bands for spectrogram extraction.
`size`	Size of the input image.
`spec_type`	type of spectrogram to extract.

fmax: int = 8000: Maximum frequency for spectrogram extraction.

model: str = '???': Name of the model to use. See https://keras.io/api/applications/ for the list of available models.

n_mels: int = 128: Number of mel bands for spectrogram extraction.

size: int | None = None: Size of the input image. If not specified, the default size of the model will be used.

spec_type: str = 'mel': type of spectrogram to extract. Can be either ‘mel’ or ‘linear’.