def update_plot2D(samples_per_class, x_select, y_select, active_tab, fold_ix,
model_path, dataset_ix, sr):
global X
global X_pca
global Y
global file_names
global feature_extractor
print('start visualization')
if (active_tab == 'tab_visualization'):
fold_name = dataset.fold_list[fold_ix]
exp_folder_fold = conv_path(os.path.join(model_path, fold_name))
scaler_path = os.path.join(exp_folder_fold, 'scaler.pickle')
scaler = load_pickle(scaler_path)
dataset_name = options_datasets[dataset_ix]['label']
params_dataset = params['datasets'][dataset_name]
folds_train, folds_val, _ = evaluation_setup(
fold_name, dataset.fold_list, params_dataset['evaluation_mode'])
print(feature_extractor)
data_gen_train = DataGenerator(
dataset,
feature_extractor,
folds=folds_train,
batch_size=params['train']['batch_size'],
shuffle=True,
train=False,
scaler=scaler)
X_list, Y_list = data_gen_train.get_data()
file_names = data_gen_train.audio_file_list
# file_names = data_gen_train.convert_features_path_to_audio_path(
# file_names, sr=sr)
Xt = []
Yt = []
for j in range(len(X_list)):
ix = int(len(X_list[j]) / 2) if len(X_list[j]) > 1 else 0
Xj = np.expand_dims(X_list[j][ix], 0)
Yj = np.expand_dims(Y_list[j][ix], 0)
Xt.append(Xj)
Yt.append(Yj)
X = np.concatenate(Xt, axis=0)
Yt = np.concatenate(Yt, axis=0)
with graph.as_default():
model_container.load_model_weights(exp_folder_fold)
X_emb = model_container.get_intermediate_output(-2, X)
# output_select
pca = PCA(n_components=4)
pca.fit(X_emb)
X_pca = pca.transform(X_emb)
print('pca', X_pca.shape, Yt.shape)
figure2D = generate_figure2D(X_pca,
Yt,
dataset.label_list,
pca_components=[x_select, y_select],
samples_per_class=samples_per_class)
return [figure2D]
def test_load_pickle():
filename = "./test.pickle"
obj = [np.zeros((2, 1))]
_clean(filename)
save_pickle(obj, filename)
obj_loaded = load_pickle(filename)
assert type(obj_loaded) is list
assert len(obj_loaded) == 1
assert np.allclose(obj, obj_loaded)
_clean(filename)
def evaluate_model(n_clicks, fold_ix, model_path):
global X_test
global X_pca_test
global file_names_test
global Y_test
global predictions
global data_generator_test
print('Change tab evaluation')
# if (active_tab == "tab_evaluation") and (fold_ix is not None):
if (n_clicks is not None) and (fold_ix is not None):
print('Start evaluation')
fold_name = dataset.fold_list[fold_ix]
exp_folder_fold = conv_path(os.path.join(model_path, fold_name))
scaler_path = os.path.join(exp_folder_fold, 'scaler.pickle')
scaler = load_pickle(scaler_path)
data_generator_test = DataGenerator(
dataset,
feature_extractor,
folds=[fold_name],
batch_size=params['train']['batch_size'],
shuffle=True,
train=False,
scaler=scaler)
print('Loading data...')
X_test, Y_test = data_generator_test.get_data()
print('Done')
print(len(X_test), len(Y_test))
with graph.as_default():
model_container.load_model_weights(exp_folder_fold)
results = model_container.evaluate((X_test, Y_test),
label_list=dataset.label_list)
results = results['classification'].results()
accuracy = results['overall']['accuracy']
class_wise = results['class_wise']
metrics = []
for label in dataset.label_list:
metrics.append(class_wise[label]['accuracy']['accuracy'])
print(metrics)
figure_metrics = generate_figure_metrics(dataset.label_list, metrics)
msg = "Accuracy in fold %s is %1.2f" % (fold_name, accuracy)
return [msg, figure_metrics]
return ['Pa']
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]])
def generate_demo(n_clicks, list_of_contents, fold_ix, model_path,
list_of_names, list_of_dates, sr):
print('generate demo')
ctx = dash.callback_context
button_id = ctx.triggered[0]['prop_id'].split('.')[0]
print(button_id, n_clicks)
if (n_clicks is not None) & (button_id == 'btn_run_demo'):
fold_name = dataset.fold_list[fold_ix]
exp_folder_fold = conv_path(os.path.join(model_path, fold_name))
scaler_path = os.path.join(exp_folder_fold, 'scaler.pickle')
scaler = load_pickle(scaler_path)
data_generator_test = DataGenerator(
dataset,
feature_extractor,
folds=[fold_name],
batch_size=params['train']['batch_size'],
shuffle=True,
train=False,
scaler=scaler)
n_files = len(data_generator_test.audio_file_list)
ix = np.random.randint(n_files)
fold_name = dataset.fold_list[fold_ix]
exp_folder_fold = conv_path(os.path.join(model_path, fold_name))
X_features, Y_file = data_generator_test.get_data_from_file(ix)
with graph.as_default():
model_container.load_model_weights(exp_folder_fold)
Y_features = model_container.model.predict(X_features)
fig_demo = generate_figure_features(X_features, Y_features,
dataset.label_list)
audio_file = data_generator_test.audio_file_list[ix]
audio_data, sr = sf.read(audio_file['file_original'])
class_ix = np.argmax(Y_file[0])
file_label = dataset.label_list[class_ix]
return [
fig_demo, {
'autoPlay': False,
'src': encode_audio(audio_data, sr)
},
'ground-truth: %s' % file_label
]
if button_id == 'upload-data':
fold_name = dataset.fold_list[fold_ix]
exp_folder_fold = conv_path(os.path.join(model_path, fold_name))
scaler_path = os.path.join(exp_folder_fold, 'scaler.pickle')
scaler = load_pickle(scaler_path)
filename = conv_path('upload.wav')
data = list_of_contents.encode("utf8").split(b";base64,")[1]
with open(filename, "wb") as fp:
fp.write(base64.decodebytes(data))
X_feat = feature_extractor.calculate(filename)
X_feat = scaler.transform(X_feat)
with graph.as_default():
Y_t = model_container.model.predict(X_feat)
label_list = dataset.label_list
figure_features = generate_figure_features(X_feat, Y_t, label_list)
return [
figure_features, {
'autoPlay': False,
'src': list_of_contents
}, ""
]
X_feat = np.zeros((10, 128, 64))
Y_t = np.zeros((10, 10))
label_list = [] * 10
figure_features = generate_figure_features(X_feat, Y_t, label_list)
return [figure_features, {'autoPlay': False, 'src': ""}, ""]