def lstm_example():
to_flatten = False
x_train, x_test, y_train, y_test, num_labels = extract_data(
flatten=to_flatten)
y_train = np_utils.to_categorical(y_train)
y_test_train = np_utils.to_categorical(y_test)
#train the model
# print('Starting LSTM')
# model = LSTM(input_shape=x_train[0].shape,
# num_classes=num_labels)
# print('x shape', x_train[0].shape)
# print('num labels',num_labels)
#
# model.train(x_train, y_train, x_test, y_test_train, n_epochs=50)
# model.evaluate(x_test, y_test)
# model.save_model()
newmodel = LSTM(input_shape=x_train[0].shape, num_classes=num_labels)
newmodel.load_model(to_load="./LSTM_best_model.h5")
newmodel.train(x_train, y_train, x_test, y_test_train, n_epochs=0)
audio_file = "../dataset/union-interview.wav"
section_by_section_analysis(model=newmodel,
audio_file=audio_file,
to_flatten=to_flatten)
def lstm_example():
to_flatten = False
x_train, x_test, y_train, y_test, num_labels = extract_data(
flatten=to_flatten)
y_train = np_utils.to_categorical(y_train)
y_test_train = np_utils.to_categorical(y_test)
print('Starting LSTM')
model = LSTM(input_shape=x_train[0].shape, num_classes=num_labels)
model.train(x_train, y_train, x_test, y_test_train, n_epochs=50)
model.evaluate(x_test, y_test)
filename = '../dataset/Sad/09b03Ta.wav'
print(
'prediction',
model.predict_one(
get_feature_vector_from_mfcc(filename, flatten=to_flatten)),
'Actual 3')
def dnn_example():
x_train, x_test, y_train, y_test = get_data(dataset_path=dataset_path, flatten=False)
y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)
print('Starting LSTM')
model = LSTM(input_shape=x_train[0].shape, num_classes=len(class_labels))
model.train(x_train, y_train, x_test, y_test)
model.evaluate(x_test, y_test)
print('LSTM Done\n Starting CNN')
in_shape = x_train[0].shape
x_train = x_train.reshape(x_train.shape[0], in_shape[0], in_shape[1], 1)
x_test = x_test.reshape(x_test.shape[0], in_shape[0], in_shape[1], 1)
model = CNN(input_shape=x_train[0].shape, num_classes=len(class_labels))
model.train(x_train, y_train, x_test, y_test)
model.evaluate(x_test, y_test)
print('CNN Done')
def lstm_example():
to_flatten = False
x_train, x_test, y_train, y_test, num_labels = extract_data(
flatten=to_flatten)
y_train = np_utils.to_categorical(y_train)
y_test_train = np_utils.to_categorical(y_test)
print('Starting LSTM')
model = LSTM(input_shape=x_train[0].shape,
num_classes=num_labels, save_path="./lstm.h5")
print("Training")
model.train(x_train, y_train, x_test, y_test_train, n_epochs=10)
print("Evaluating")
model.evaluate(x_test, y_test)
model.save_model()
filename = '../dataset/Sad/09b03Ta.wav'
# filename = './laugh.wav'
print("\nPredicted: {}\nActual: {}".format(
get_class_name(
model.predict_one(
get_feature_vector_from_mfcc(filename, flatten=to_flatten))),
get_class_name(2)))
female_mfccs = female_mfccs[:common]
data = male_mfccs + female_mfccs
labels = [0 for _ in male_mfccs] + [1 for _ in female_mfccs]
return np.array(data), np.array(labels)
if __name__ == '__main__':
train_test_factor = 0.8
# get training data
data, labels = prepare_training_data(
'/home/rfeldhans/programming/audio/esiaf_gender_rec/dataset/', 6000)
# schuffle for train/test assignment
x, y = _shuffle(data, labels)
x_train = np.array(x[:int(len(x) * train_test_factor)])
y_train = np.array(y[:int(len(y) * train_test_factor)])
x_test = np.array(x[int(len(x) * train_test_factor):])
y_test = np.array(y[int(len(y) * train_test_factor):])
# prepare labels
y_train = np_utils.to_categorical(y_train)
y_train_test = np_utils.to_categorical(y_test)
model = LSTM(input_shape=x_train[0].shape, num_classes=2)
model.train(x_train, y_train, x_test, y_train_test, n_epochs=20)
model.evaluate(x_test, y_test)
model.save_model()