def select_feature(feature_ix):
if feature_ix is not None:
features_name = options_features[feature_ix]['label']
features_class = get_available_features()[features_name]
default_arguments = get_default_args_of_function(
features_class.__init__)
delete = [
'sequence_time', 'sequence_hop_time', 'audio_win', 'audio_hop',
'sr'
]
for key in delete:
default_arguments.pop(key)
if features_name in params['features']:
params_features = params['features'][features_name]
for key in params_features.keys():
default_arguments[key] = params_features[key]
return [str(default_arguments)]
else:
return [""]
def do_features_extraction(status_features, feature_ix, sequence_time,
sequence_hop_time, audio_hop, audio_win, sr,
specific_parameters, dataset_path, audio_folder,
features_folder, dataset_ix):
global feature_extractor
if status_features != 'EXTRACTING':
# return [False, '', 'success', 'True']
raise dash.exceptions.PreventUpdate
if feature_ix is None:
return [True, 'Please select a Feature name', 'danger', 'True']
if dataset_ix is None:
return [True, 'Please select a dataset', 'danger', 'True']
features_name = options_features[feature_ix]['label']
dataset_name = options_datasets[dataset_ix]['label']
feature_extractor_class = get_available_features()[features_name]
specific_parameters = ast.literal_eval(specific_parameters)
feature_extractor = feature_extractor_class(
sequence_time=sequence_time,
sequence_hop_time=sequence_hop_time,
audio_win=audio_win,
audio_hop=audio_hop,
sr=sr,
**specific_parameters)
# get dataset class
dataset_class = get_available_datasets()[dataset_name]
dataset = dataset_class(dataset_path)
if not dataset.check_if_downloaded():
return [
True,
'Please download the dataset before doing feature extraction',
'danger'
]
print('Extracting features...')
feature_extractor.extract(dataset)
print('Done!')
return [True, 'Features extracted', 'success', 'True']
def main():
# Parse arguments
parser = argparse.ArgumentParser(
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument(
'-d',
'--dataset',
type=str,
help='dataset name (e.g. UrbanSound8k, ESC50, URBAN_SED, SONYC_UST)',
default='UrbanSound8k')
parser.add_argument(
'-f',
'--features',
type=str,
help='features name (e.g. Spectrogram, MelSpectrogram, Openl3)',
default='MelSpectrogram')
parser.add_argument('-p',
'--path',
type=str,
help='path to the parameters.json file',
default='../')
parser.add_argument(
'-m',
'--model',
type=str,
help='model name (e.g. MLP, SB_CNN, SB_CNN_SED, A_CRNN, VGGish)',
default='SB_CNN')
parser.add_argument('-fold',
'--fold_name',
type=str,
help='fold name',
default='fold1')
parser.add_argument('-s',
'--models_path',
type=str,
help='path to save the trained model',
default='../trained_models')
parser.add_argument('--aug', dest='augmentation', action='store_true')
parser.add_argument('--no-aug', dest='augmentation', action='store_false')
parser.set_defaults(augmentation=False)
args = parser.parse_args()
print(__doc__)
if args.dataset not in get_available_datasets():
raise AttributeError('Dataset not available')
if args.features not in get_available_features():
raise AttributeError('Features not available')
if args.model not in get_available_models():
raise AttributeError('Model not available')
# Get parameters
parameters_file = os.path.join(args.path, 'parameters.json')
params = load_json(parameters_file)
params_dataset = params['datasets'][args.dataset]
params_features = params['features']
params_model = params['models'][args.model]
# Get and init dataset class
dataset_class = get_available_datasets()[args.dataset]
dataset_path = os.path.join(args.path, params_dataset['dataset_path'])
dataset = dataset_class(dataset_path)
if args.fold_name not in dataset.fold_list:
raise AttributeError('Fold not available')
# Data augmentation
if args.augmentation:
# Define the augmentations
augmentations = params['data_augmentations']
# Initialize AugmentedDataset
dataset = AugmentedDataset(dataset, params['features']['sr'],
augmentations)
# Process all files
print('Doing data augmentation ...')
dataset.process()
print('Done!')
# Get and init feature class
features_class = get_available_features()[args.features]
features = features_class(
sequence_time=params_features['sequence_time'],
sequence_hop_time=params_features['sequence_hop_time'],
audio_win=params_features['audio_win'],
audio_hop=params_features['audio_hop'],
sr=params_features['sr'],
**params_features[args.features])
print('Features shape: ', features.get_shape())
# Check if features were extracted
if not features.check_if_extracted(dataset):
print('Extracting features ...')
features.extract(dataset)
print('Done!')
use_validate_set = True
if args.dataset in ['TUTSoundEvents2017', 'ESC50', 'ESC10']:
# When have less data, don't use validation set.
use_validate_set = False
folds_train, folds_val, _ = evaluation_setup(
args.fold_name,
dataset.fold_list,
params_dataset['evaluation_mode'],
use_validate_set=use_validate_set)
data_gen_train = DataGenerator(dataset,
features,
folds=folds_train,
batch_size=params['train']['batch_size'],
shuffle=True,
train=True,
scaler=None)
scaler = Scaler(normalizer=params_model['normalizer'])
print('Fitting scaler ...')
scaler.fit(data_gen_train)
print('Done!')
# Pass scaler to data_gen_train to be used when data
# loading
data_gen_train.set_scaler(scaler)
data_gen_val = DataGenerator(dataset,
features,
folds=folds_val,
batch_size=params['train']['batch_size'],
shuffle=False,
train=False,
scaler=scaler)
# Define model
features_shape = features.get_shape()
n_frames_cnn = features_shape[1]
n_freq_cnn = features_shape[2]
n_classes = len(dataset.label_list)
model_class = get_available_models()[args.model]
metrics = ['classification']
if args.dataset in sed_datasets:
metrics = ['sed']
if args.dataset in tagging_datasets:
metrics = ['tagging']
model_container = model_class(model=None,
model_path=None,
n_classes=n_classes,
n_frames_cnn=n_frames_cnn,
n_freq_cnn=n_freq_cnn,
metrics=metrics,
**params_model['model_arguments'])
model_container.model.summary()
# Set paths
model_folder = os.path.join(args.models_path, args.model, args.dataset)
exp_folder = os.path.join(model_folder, args.fold_name)
mkdir_if_not_exists(exp_folder, parents=True)
# Save model json and scaler
model_container.save_model_json(model_folder)
save_pickle(scaler, os.path.join(exp_folder, 'scaler.pickle'))
# data_train = data_gen_train.get_data()
# data_val = data_gen_val.get_data()
# Train model
model_container.train(
data_gen_train,
data_gen_val,
# data_train, data_val,
label_list=dataset.label_list,
weights_path=exp_folder,
**params['train'],
sequence_time_sec=params_features['sequence_hop_time'])
def main():
# Parse arguments
parser = argparse.ArgumentParser(
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter
)
parser.add_argument(
'-od', '--origin_dataset', type=str,
help='dataset name (e.g. UrbanSound8k, ESC50, URBAN_SED, SONYC_UST)',
default='UrbanSound8k'
)
parser.add_argument(
'-ofold', '--origin_fold_name', type=str,
help='origin fold name',
default='fold1')
parser.add_argument(
'-d', '--dataset', type=str,
help='dataset name (e.g. UrbanSound8k, ESC50, URBAN_SED, SONYC_UST)',
default='ESC50'
)
parser.add_argument(
'-fold', '--fold_name', type=str,
help='destination fold name',
default='fold1')
parser.add_argument(
'-f', '--features', type=str,
help='features name (e.g. Spectrogram, MelSpectrogram, Openl3)',
default='MelSpectrogram'
)
parser.add_argument(
'-p', '--path', type=str,
help='path to the parameters.json file',
default='../'
)
parser.add_argument(
'-m', '--model', type=str,
help='model name (e.g. MLP, SB_CNN, SB_CNN_SED, A_CRNN, VGGish)',
default='SB_CNN')
parser.add_argument(
'-s', '--models_path', type=str,
help='path to save the trained model',
default='../trained_models'
)
args = parser.parse_args()
print(__doc__)
if args.dataset not in get_available_datasets():
raise AttributeError('Dataset not available')
if args.features not in get_available_features():
raise AttributeError('Features not available')
if args.model not in get_available_models():
raise AttributeError('Model not available')
# Get parameters
parameters_file = os.path.join(args.path, 'parameters.json')
params = load_json(parameters_file)
params_dataset = params['datasets'][args.dataset]
params_features = params['features']
params_model = params['models'][args.model]
# Load origin model
model_path_origin = os.path.join(args.models_path, args.model,
args.origin_dataset)
model_class = get_available_models()[args.model]
metrics = ['accuracy']
if args.dataset in sed_datasets:
metrics = ['sed']
model_container = model_class(
model=None, model_path=model_path_origin,
metrics=metrics
)
model_container.load_model_weights(
os.path.join(model_path_origin, args.origin_fold_name))
kwargs = {}
if args.dataset in sed_datasets:
kwargs = {'sequence_hop_time': params_features['sequence_hop_time']}
# Get and init dataset class
dataset_class = get_available_datasets()[args.dataset]
dataset_path = os.path.join(args.path, params_dataset['dataset_path'])
dataset = dataset_class(dataset_path, **kwargs)
if args.fold_name not in dataset.fold_list:
raise AttributeError('Fold not available')
# Get and init feature class
features_class = get_available_features()[args.features]
features = features_class(
sequence_time=params_features['sequence_time'],
sequence_hop_time=params_features['sequence_hop_time'],
audio_win=params_features['audio_win'],
audio_hop=params_features['audio_hop'],
sr=params_features['sr'], **params_features[args.features]
)
print('Features shape: ', features.get_shape())
# Check if features were extracted
if not features.check_if_extracted(dataset):
print('Extracting features ...')
features.extract(dataset)
print('Done!')
use_validate_set = True
if args.dataset in ['TUTSoundEvents2017', 'ESC50', 'ESC10']:
# When have less data, don't use validation set.
use_validate_set = False
folds_train, folds_val, _ = evaluation_setup(
args.fold_name, dataset.fold_list,
params_dataset['evaluation_mode'],
use_validate_set=use_validate_set
)
data_gen_train = DataGenerator(
dataset, features, folds=folds_train,
batch_size=params['train']['batch_size'],
shuffle=True, train=True, scaler=None
)
scaler = Scaler(normalizer=params_model['normalizer'])
print('Fitting features ...')
scaler.fit(data_gen_train)
print('Done!')
data_gen_train.set_scaler(scaler)
data_gen_val = DataGenerator(
dataset, features, folds=folds_val,
batch_size=params['train']['batch_size'],
shuffle=False, train=False, scaler=scaler
)
# Fine-tune model
n_classes = len(dataset.label_list)
layer_where_to_cut = -2
model_container.fine_tuning(layer_where_to_cut,
new_number_of_classes=n_classes,
new_activation='sigmoid',
freeze_source_model=True)
model_container.model.summary()
# Set paths
model_folder = os.path.join(
args.models_path, args.model,
args.origin_dataset+'_ft_'+args.dataset)
exp_folder = os.path.join(model_folder, args.fold_name)
mkdir_if_not_exists(exp_folder, parents=True)
# Save model json and scaler
model_container.save_model_json(model_folder)
save_pickle(scaler, os.path.join(exp_folder, 'scaler.pickle'))
# Train model
model_container.train(
data_gen_train, data_gen_val,
label_list=dataset.label_list,
weights_path=exp_folder,
sequence_time_sec=params_features['sequence_hop_time'],
**params['train'])
def main():
# Parse arguments
parser = argparse.ArgumentParser(
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument(
'-d',
'--dataset',
type=str,
help='dataset name (e.g. UrbanSound8k, ESC50, URBAN_SED, SONYC_UST)',
default='UrbanSound8k')
parser.add_argument(
'-f',
'--features',
type=str,
help='features name (e.g. Spectrogram, MelSpectrogram, Openl3)',
default='MelSpectrogram')
parser.add_argument('-p',
'--path',
type=str,
help='path to the parameters.json file',
default='../')
args = parser.parse_args()
print(__doc__)
if args.dataset not in get_available_datasets():
raise AttributeError('Dataset not available')
if args.features not in get_available_features():
raise AttributeError('Features not available')
# Get parameters
parameters_file = os.path.join(args.path, 'parameters.json')
params = load_json(parameters_file)
params_dataset = params['datasets'][args.dataset]
params_features = params['features']
# Get and init dataset class
dataset_class = get_available_datasets()[args.dataset]
dataset_path = os.path.join(args.path, params_dataset['dataset_path'])
dataset = dataset_class(dataset_path)
# Get and init feature class
features_class = get_available_features()[args.features]
features = features_class(
sequence_time=params_features['sequence_time'],
sequence_hop_time=params_features['sequence_hop_time'],
audio_win=params_features['audio_win'],
audio_hop=params_features['audio_hop'],
sr=params_features['sr'],
**params_features[args.features])
# Extract features
if features.check_if_extracted(dataset):
print('%s features were already extracted for %s dataset. ' %
(args.features, args.dataset))
else:
print('Extracting features ...')
features.extract(dataset)
print('Done!')
def main():
# Parse arguments
parser = argparse.ArgumentParser(
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument(
'-d',
'--dataset',
type=str,
help='dataset name (e.g. UrbanSound8k, ESC50, URBAN_SED, SONYC_UST)',
default='UrbanSound8k')
parser.add_argument(
'-f',
'--features',
type=str,
help='features name (e.g. Spectrogram, MelSpectrogram, Openl3)',
default='MelSpectrogram')
parser.add_argument('-p',
'--path',
type=str,
help='path to the parameters.json file',
default='../')
parser.add_argument(
'-m',
'--model',
type=str,
help='model name (e.g. MLP, SB_CNN, SB_CNN_SED, A_CRNN, VGGish)',
default='SB_CNN')
parser.add_argument('-fold',
'--fold_name',
type=str,
help='fold name',
default='fold1')
parser.add_argument('-s',
'--models_path',
type=str,
help='path to load the trained model',
default='../trained_models')
parser.add_argument(
'-ft',
'--fine_tuning',
type=str,
help='fine-tuned dataset name (e.g. UrbanSound8k, ESC50, URBAN_SED)',
)
args = parser.parse_args()
print(__doc__)
if args.dataset not in get_available_datasets():
raise AttributeError('Dataset not available')
if args.features not in get_available_features():
raise AttributeError('Features not available')
if args.model not in get_available_models():
raise AttributeError('Model not available')
# Get parameters
parameters_file = os.path.join(args.path, 'parameters.json')
params = load_json(parameters_file)
params_features = params['features']
dataset_name = (args.dataset
if args.fine_tuning is None else args.fine_tuning)
params_dataset = params['datasets'][dataset_name]
# Get and init dataset class
dataset_class = get_available_datasets()[dataset_name]
dataset_path = os.path.join(args.path, params_dataset['dataset_path'])
dataset = dataset_class(dataset_path)
if args.fold_name not in dataset.fold_list:
raise AttributeError('Fold not available')
# Get and init feature class
features_class = get_available_features()[args.features]
features = features_class(
sequence_time=params_features['sequence_time'],
sequence_hop_time=params_features['sequence_hop_time'],
audio_win=params_features['audio_win'],
audio_hop=params_features['audio_hop'],
sr=params_features['sr'],
**params_features[args.features])
# Check if features were extracted
if not features.check_if_extracted(dataset):
print('Extracting features ...')
features.extract(dataset)
print('Done!')
# Set paths
if args.fine_tuning is None:
dataset_path = args.dataset
else:
dataset_path = args.dataset + '_ft_' + args.fine_tuning
model_folder = os.path.join(args.models_path, args.model, dataset_path)
exp_folder = os.path.join(model_folder, args.fold_name)
# Load scaler
scaler_file = os.path.join(exp_folder, 'scaler.pickle')
scaler = load_pickle(scaler_file)
# Init data generator
data_gen_test = DataGenerator(dataset,
features,
folds=[args.fold_name],
batch_size=params['train']['batch_size'],
shuffle=False,
train=False,
scaler=scaler)
# Load model and best weights
model_class = get_available_models()[args.model]
metrics = ['classification']
if dataset_name in sed_datasets:
metrics = ['sed']
if args.dataset in tagging_datasets:
metrics = ['tagging']
model_container = model_class(model=None,
model_path=model_folder,
metrics=metrics)
model_container.load_model_weights(exp_folder)
kwargs = {}
if dataset_name in sed_datasets:
kwargs = {
'sequence_time_sec': params_features['sequence_hop_time'],
'metric_resolution_sec': 1.0
}
results = model_container.evaluate(data_gen_test,
label_list=dataset.label_list,
**kwargs)
print(results[metrics[0]])
# dbc.Col(dbc.Input(type="number", id="n_fft", placeholder="n_fft",
# value=params_features['n_fft']), width=4,),
dbc.Label("sampling rate", html_for="example-email-row", width=2),
dbc.Col(
dbc.Input(type="number",
id="sr",
placeholder="sr",
value=params_features['sr']),
width=4,
),
],
row=True,
)
# Features selector
features_classes = get_available_features()
options_features = [{
'label': name,
'value': value
} for value, name in enumerate(features_classes.keys())]
feature_selector = dbc.FormGroup(
[
dbc.Label("Feature", html_for="dropdown", width=2),
dbc.Col(dcc.Dropdown(id="feature_name", options=options_features),
width=10),
],
row=True,
)
# Specific parameters of features selected
specific_parameters = dbc.Textarea(id='specific_parameters',
def create_model(n_clicks_create_model, n_clicks_load_model, model_ix,
feature_ix, dataset_ix, model_parameters, sequence_time,
sequence_hop_time, audio_hop, audio_win, sr,
specific_parameters, dataset_path, audio_folder,
features_folder, model_path):
global model_container
global feature_extractor
global dataset
ctx = dash.callback_context
if (n_clicks_create_model is None) & (n_clicks_load_model is None):
return [False, "", 'success', '']
else:
button_id = ctx.triggered[0]['prop_id'].split('.')[0]
if (button_id == 'create_model') | (button_id == 'load_model'):
if model_ix is None:
return [True, 'Please select a Model', 'danger', '']
if feature_ix is None:
return [True, 'Please select a Feature extractor', 'danger', '']
if dataset_ix is None:
return [True, 'Please select a Dataset', 'danger', '']
model_name = options_models[model_ix]['label']
feature_name = options_features[feature_ix]['label']
dataset_name = options_datasets[dataset_ix]['label']
feature_extractor_class = get_available_features()[feature_name]
specific_parameters = ast.literal_eval(specific_parameters)
feature_extractor = feature_extractor_class(
sequence_time=sequence_time,
sequence_hop_time=sequence_hop_time,
audio_win=audio_win,
audio_hop=audio_hop,
sr=sr,
**specific_parameters)
features_shape = feature_extractor.get_shape()
n_frames_cnn = features_shape[1]
n_freq_cnn = features_shape[2]
# get dataset class
dataset_class = get_available_datasets()[dataset_name]
# init data_generator
kwargs = {}
if dataset_name == 'URBAN_SED':
kwargs = {'sequence_hop_time': sequence_hop_time}
dataset = dataset_class(dataset_path, **kwargs)
n_classes = len(dataset.label_list)
model_class = get_available_models()[model_name]
model_parameters = ast.literal_eval(model_parameters)
if (button_id == 'create_model'):
with graph.as_default():
model_container = model_class(model=None,
model_path=None,
n_classes=n_classes,
n_frames_cnn=n_frames_cnn,
n_freq_cnn=n_freq_cnn,
**model_parameters)
model_container.model.summary()
if model_name == 'VGGish':
model_container.load_pretrained_model_weights()
model_container.fine_tuning(
-1,
new_number_of_classes=n_classes,
new_activation='softmax',
freeze_source_model=True)
stringlist = []
model_container.model.summary(
print_fn=lambda x: stringlist.append(x))
summary = "\n".join(stringlist)
mkdir_if_not_exists(conv_path(os.path.dirname(model_path)))
mkdir_if_not_exists(conv_path(model_path))
model_container.save_model_json(conv_path(model_path))
return [True, 'Model created', 'success', summary]
if (button_id == 'load_model'):
with graph.as_default():
model_container = model_class(model=None,
model_path=conv_path(model_path))
model_container.model.summary()
stringlist = []
model_container.model.summary(
print_fn=lambda x: stringlist.append(x))
summary = "\n".join(stringlist)
return [True, 'Model loaded', 'success', summary]
# model_container.save_model_weights(model_path)
return [False, "", 'success', '']
def check_pipeline(feature_ix, sequence_time, sequence_hop_time, audio_hop,
audio_win, sr, specific_parameters, dataset_path,
audio_folder, features_folder, dataset_ix,
end_features_extraction, status_features, model_parameters,
model_path, model_ix):
global model_container
global feature_extractor
global data_generator_train
ctx = dash.callback_context
button_id = ctx.triggered[0]['prop_id'].split('.')[0]
# if was trigger by end_features_extraction and
# the features were already calculated
if button_id == 'end_features_extraction' and \
status_features == 'NOT_EXTRACTING':
raise dash.exceptions.PreventUpdate
feature_extractor = None
if feature_ix is not None:
feature_name = (options_features[feature_ix]['label']
if feature_ix is not None else "")
feature_extractor_class = get_available_features()[feature_name]
specific_parameters = ast.literal_eval(specific_parameters)
feature_extractor = feature_extractor_class(
sequence_time=sequence_time,
sequence_hop_time=sequence_hop_time,
audio_win=audio_win,
audio_hop=audio_hop,
sr=sr,
**specific_parameters)
checks = []
if dataset_ix is not None:
dataset_name = options_datasets[dataset_ix]['label']
# get dataset class
dataset_class = get_available_datasets()[dataset_name]
dataset = dataset_class(dataset_path)
if dataset.check_if_downloaded():
checks.append('dataset')
if feature_ix is not None:
features_extracted = feature_extractor.check_if_extracted(dataset)
if features_extracted:
checks.append('features')
if model_ix is not None:
model_name = options_models[model_ix]['label']
features_shape = feature_extractor.get_shape()
n_frames_cnn = features_shape[1]
n_freq_cnn = features_shape[2]
n_classes = len(dataset.label_list)
model_class = get_available_models()[model_name]
model_parameters = ast.literal_eval(model_parameters)
with graph.as_default():
model_container = model_class(model=None,
model_path=None,
n_classes=n_classes,
n_frames_cnn=n_frames_cnn,
n_freq_cnn=n_freq_cnn,
**model_parameters)
if model_name == 'VGGish':
model_container.load_pretrained_model_weights()
model_container.fine_tuning(
-1,
new_number_of_classes=n_classes,
new_activation='softmax',
freeze_source_model=True)
model_exists = model_container.check_if_model_exists(
conv_path(model_path))
if model_exists:
checks.append('model')
return [checks]