def TestModel(self, datapath='', str_dataset='dev', data_count=32):
'''
测试检验模型效果
'''
data = DataSpeech(self.datapath, str_dataset)
#data = self.data
#data.LoadDataList(str_dataset)
num_data = data.GetDataNum() # 获取数据的数量
if (data_count <= 0 or data_count >
num_data): # 当data_count为小于等于0或者大于测试数据量的值时，则使用全部数据来测试
data_count = num_data
try:
ran_num = random.randint(0, num_data - 1) # 获取一个随机数
words_num = 0
word_error_num = 0
for i in range(data_count):
data_input, data_labels = data.GetData(
(ran_num + i) % num_data) # 从随机数开始连续向后取一定数量数据
pre = self.Predict(data_input, data_input.shape[0] // 4)
words_num += max(data_labels.shape[0], pre.shape[0])
word_error_num += GetEditDistance(data_labels, pre)
print('*[测试结果] 语音识别语音单字错误率：', word_error_num / words_num * 100,
'%')
except StopIteration:
print('[Error] Model Test Error. please check data format.')
def TrainModel(self,
datapath,
epoch=2,
save_step=1000,
filename='model_speech/LSTM_CNN_model'):
'''
训练模型
参数：
datapath: 数据保存的路径
epoch: 迭代轮数
save_step: 每多少步保存一次模型
filename: 默认保存文件名，不含文件后缀名
'''
data = DataSpeech(datapath)
data.LoadDataList('train')
num_data = DataSpeech.GetDataNum() # 获取数据的数量
for epoch in range(epoch): # 迭代轮数
print('[running] train epoch %d .' % epoch)
n_step = 0 # 迭代数据数
while True:
try:
print('[message] epoch %d . Have train datas %d+' %
(epoch, n_step * save_step))
# data_genetator是一个生成器函数
yielddatas = data.data_genetator(self.BATCH_SIZE)
self._model.fit_generator(yielddatas,
save_step,
nb_worker=2)
n_step += 1
except StopIteration:
print('[error] generator error. please check data format.')
break
self.SaveModel(comment='_e_' + str(epoch) + '_step_' +
str(n_step))
def TestModel(self, datapath='', str_dataset='dev', data_count=32):
'''
测试检验模型效果
'''
data = DataSpeech(self.datapath, str_dataset)
#data = self.data
#data.LoadDataList(str_dataset)
num_data = data.GetDataNum() # 获取数据的数量
if (data_count <= 0 or data_count >
num_data): # 当data_count为小于等于0或者大于测试数据量的值时，则使用全部数据来测试
data_count = num_data
try:
gen = data.data_genetator(data_count)
#for i in range(1):
# [X, y, input_length, label_length ], labels = gen
#r = self._model.test_on_batch([X, y, input_length, label_length ], labels)
r = self._model.evaluate_generator(generator=gen,
steps=1,
max_queue_size=data_count,
workers=1,
use_multiprocessing=False)
print(r)
except StopIteration:
print('[Error] Model Test Error. please check data format.')
def TestModel(self, datapath, str_dataset='dev'):
'''
测试检验模型效果
'''
data = DataSpeech(datapath)
data.LoadDataList(str_dataset)
num_data = DataSpeech.GetDataNum() # 获取数据的数量
try:
gen = data.data_genetator(num_data)
for i in range(1):
X, y = gen
r = self._model.test_on_batch(X, y)
print(r)
except StopIteration:
print('[Error] Model Test Error. please check data format.')