def load_dataset(self, csv='./dataset/tess/dataset.csv'):
handle = open(csv, 'r')
rawlines = handle.read().split('\n')
handle.close()
datalist = [line.split(',') for line in rawlines]
shuffle(datalist)
processed_x = []
processed_y = []
for filename, target_emotion in datalist:
if filename in ['YAF_germ_angry.wav']: continue
rate, signal = wav.read('./dataset/tess/' + target_emotion + '/' +
filename)
filter_bank_feature = log_filter_bank(signal, rate)
processed_x.append(filter_bank_feature[:self.num_sample, :])
processed_y.append(self.EMOTIONS[target_emotion])
# print('\nemotion:', target_emotion)
# print(filter_bank_feature[:self.num_sample, :])
processed_x = np.array(processed_x).reshape(-1, self.num_sample, 26, 1)
processed_y = np_utils.to_categorical(processed_y)
train_data_ratio = 0.9
num_train_data = int(len(datalist) * train_data_ratio)
self.train_data_x = processed_x[:num_train_data]
self.train_data_y = processed_y[:num_train_data]
self.test_data_x = processed_x[num_train_data:]
self.test_data_y = processed_y[num_train_data:]
def load_dataset2(self, csv='./dataset/input.csv'):
handle = open(csv, 'r')
rawlines = handle.read().split('\n')
handle.close()
datalist = [line.split(',') for line in rawlines]
shuffle(datalist)
cnt = 0
processed_x = []
processed_y = []
for url, target_emotion in datalist:
if url in ['YAF_germ_angry.wav']: continue
if cnt == 1560: break
#print(url,cnt)
rate, signal = wav.read('./dataset/tess/' + url)
filter_bank_feature = log_filter_bank(signal, rate)
#filter_bank_feature = preprocessor.process('./dataset/tess/'+url)
#processed_x.append(filter_bank_feature)
processed_x.append(filter_bank_feature[:self.num_sample, :])
processed_y.append(self.EMOTIONS[target_emotion])
cnt = cnt + 1
processed_x = np.array(processed_x).reshape(-1, self.num_sample, 26, 1)
processed_y = np_utils.to_categorical(processed_y)
train_data_ratio = 0.9
num_train_data = int(len(datalist) * train_data_ratio)
self.train_data_x = processed_x[:num_train_data]
self.train_data_y = processed_y[:num_train_data]
self.test_data_x = processed_x[num_train_data:]
self.test_data_y = processed_y[num_train_data:]
print(len(self.train_data_x))
print(len(self.train_data_y))
def process(path, num_sample=32):
rate, signal = wav.read(path)
filter_bank_feature = log_filter_bank(signal, rate)
return filter_bank_feature[:num_sample, :]
shuffle(datalist)
train_data_ratio = 0.9
num_train_data = int(len(datalist) * train_data_ratio)
train_datalist = datalist[:num_train_data]
test_datalist = datalist[num_train_data:]
x_train = []
y_train = []
num_sample = 32
for filename, target_emotion in train_datalist:
if filename in ['YAF_germ_angry.wav']: continue
# mfcc 처리
rate, signal = wav.read(DATA_STATIC_PATH + target_emotion + '/' + filename)
filter_bank_feature = log_filter_bank(signal, rate)
# 트레이닝 데이터 생성
x_train.append(filter_bank_feature[:num_sample, :])
# x_train.append(filter_bank_feature[1:3, :])
y_train.append(EMOTIONS[target_emotion])
x_train = np.array(x_train).reshape(-1, num_sample, 26, 1)
y_train = np_utils.to_categorical(y_train)
x_test = []
y_test = []
for filename, target_emotion in test_datalist:
if filename in ['YAF_germ_angry.wav']: continue