dcase_util.processors.EdgeL3ExtractorProcessor

class dcase_util.processors.EdgeL3ExtractorProcessor(fs=44100, hop_length_samples=None, hop_length_seconds=0.02, model=None, retrain_type='ft', sparsity=95.45, center=True, verbose=False, **kwargs)

Constructor

Parameters

fsint

Sampling rate of the incoming signal.

hop_length_samplesint

Hop length in samples. Default value None

hop_length_secondsfloat

Hop length in seconds. Default value 0.02

modelkeras.models.Model or None

Loaded model object. If a model is provided, then sparsity will be ignored. If None is provided, the model will be loaded using the provided sparsity value. Default value None

retrain_type{‘ft’, ‘kd’}

Type of retraining for the sparsified weights of L3 audio model. ‘ft’ chooses the fine-tuning method and ‘kd’ returns knowledge distilled model. Default value “ft”

sparsity{95.45, 53.5, 63.5, 72.3, 73.5, 81.0, 87.0, 90.5}

The desired sparsity of audio model. Default value 95.45

centerbool

If True, pads beginning of signal so timestamps correspond to center of window. Default value True

verbosebool

If True, prints verbose messages. Default value False

__init__(fs=44100, hop_length_samples=None, hop_length_seconds=0.02, model=None, retrain_type='ft', sparsity=95.45, center=True, verbose=False, **kwargs)

Constructor

Parameters

fsint

Sampling rate of the incoming signal.

hop_length_samplesint

Hop length in samples. Default value None

hop_length_secondsfloat

Hop length in seconds. Default value 0.02

modelkeras.models.Model or None

Loaded model object. If a model is provided, then sparsity will be ignored. If None is provided, the model will be loaded using the provided sparsity value. Default value None

retrain_type{‘ft’, ‘kd’}

Type of retraining for the sparsified weights of L3 audio model. ‘ft’ chooses the fine-tuning method and ‘kd’ returns knowledge distilled model. Default value “ft”

sparsity{95.45, 53.5, 63.5, 72.3, 73.5, 81.0, 87.0, 90.5}

The desired sparsity of audio model. Default value 95.45

centerbool

If True, pads beginning of signal so timestamps correspond to center of window. Default value True

verbosebool

If True, prints verbose messages. Default value False

Methods

__init__([fs, hop_length_samples, ...])	Constructor
delimiter([exclude_delimiters])	Use csv.sniffer to guess delimiter for CSV file
detect_file_format([filename])	Detect file format from extension
empty()	Check if file is empty
exists()	Checks that file exists
extract(y)	Extract features for the audio signal.
get_file_information()	Get file information, filename
get_processing_chain_item()	Get processing chain item with current Processor data.
is_package([filename])	Determine if the file is compressed package.
load([filename])	Load file
log([level])	Log container content
process([data, store_processing_chain])	Extract features
save([filename])	Save file
show([mode, indent, visualize])	Print container content
to_html([indent])	Get container information in a HTML formatted string
to_string([ui, indent])	Get container information in a string
validate_format()	Validate file format

Attributes

bytes	File size in bytes
description	Extractor description
input_type	Input data type
label	Extractor label
logger	Logger instance
md5	Checksum for file.
output_type	Output data type
valid_formats	Valid file formats