import sys
sys.path.append("../")
from classifier import Classifier
from mic import Mic
# game stuff
from game_logic import GameLogic
from levels import LevelMic
from path_collector import PathCollector
# yaml config file
cfg = yaml.safe_load(open("../config.yaml"))
# init path collector
path_coll = PathCollector(cfg, root_path='.')
# --
# mic
# create classifier
classifier = Classifier(path_coll=path_coll, verbose=True)
# create mic instance
mic = Mic(classifier=classifier,
feature_params=cfg['feature_params'],
mic_params=cfg['mic_params'],
is_audio_record=True)
# --
# game setup
format=None,
closefd=True)
return np.unique(label_list)
if __name__ == '__main__':
"""
reads recorded examples from in_path, cuts them to single examples and saves them
"""
# yaml config file
cfg = yaml.safe_load(open("./config.yaml"))
# path_collector
path_coll = PathCollector(cfg)
# create all necessary folders
path_coll.create_my_recording_folders()
# --
# cut
# get all .wav files
raw_wavs = glob(cfg['my_recordings']['in_path'] + '*.wav')
# cut them to single wavs
labels = cut_and_copy_wavs(raw_wavs,
cfg['feature_params'],
cfg['my_recordings']['wav_path'],
cfg['my_recordings']['plot_path'],
y[i*n_label:i*n_label+n_label] = y_raw[y_raw==label][:n_label]
index[i*n_label:i*n_label+n_label] = index_raw[y_raw==label][:n_label]
return x, y, index
if __name__ == '__main__':
"""
main function of audio dataset
"""
# yaml config file
cfg = yaml.safe_load(open("./config.yaml"))
# path_collector
path_coll = PathCollector(cfg)
# create all necessary folders
path_coll.create_audio_dataset_folders()
# status message
print("\n--create datasets\nexamples per class: [{}], saved at paths: {} with splits: {}\n".format(cfg['audio_dataset']['n_examples'], cfg['audio_dataset']['data_paths'], cfg['audio_dataset']['data_percs']))
# copy wav files to path
labels = create_datasets(n_examples=cfg['audio_dataset']['n_examples'], dataset_path=cfg['audio_dataset']['dataset_path'], wav_folders=path_coll.wav_folders_audio_dataset, data_percs=cfg['audio_dataset']['data_percs'], recreate=cfg['audio_dataset']['recreate'])
# --
# extract mfcc features
mic
"""
import yaml
import matplotlib.pyplot as plt
import soundfile
from plots import plot_waveform
from common import create_folder
from path_collector import PathCollector
# yaml config file
cfg = yaml.safe_load(open("./config.yaml"))
# init path collector
path_coll = PathCollector(cfg)
# create folder
create_folder([cfg['mic_params']['plot_path']])
# window and hop size
N, hop = int(
cfg['feature_params']['N_s'] * cfg['feature_params']['fs']), int(
cfg['feature_params']['hop_s'] * cfg['feature_params']['fs'])
# classifier
classifier = Classifier(path_coll=path_coll, verbose=True)
# create mic instance
mic = Mic(classifier=classifier,
feature_params=cfg['feature_params'],
logging.basicConfig(filename=log_path + 'ml.log', level=logging.DEBUG, format='%(asctime)s %(message)s')
# disable unwanted logs
logging.getLogger('matplotlib.font_manager').disabled = True
if __name__ == '__main__':
"""
ML - Machine Learning file
"""
# yaml config file
cfg = yaml.safe_load(open("./config.yaml"))
# init path collector
path_coll = PathCollector(cfg)
# create all necessary folders
path_coll.create_ml_folders()
# init logging
init_logging(cfg['ml']['paths']['log'])
# --
# batches
# create batch archiv
batch_archiv = BatchArchiv(path_coll.mfcc_data_files_all, batch_size=cfg['ml']['train_params']['batch_size'])