def train(self):
model = self.__build_model()
# 每个epoch之后保存模型
checkpoint = ModelCheckpoint(os.path.join(self.model_path,
'weights.{epoch:03d}.h5'),
monitor='val_acc',
verbose=1,
save_best_only=True,
mode='auto')
# 连续三次epoch某个观察项没有改善，则提前退出训练，默认观察项是val_acc
early_stop = EarlyStopping(patience=3, verbose=1)
history = model.fit(self.x_train,
self.y_train,
batch_size=self.batch_size,
epochs=self.epochs,
verbose=1,
callbacks=[checkpoint, early_stop],
validation_data=(self.x_test, self.y_test))
# 训练结束后，最后保存一次模型，其实没有必要
model.save(os.path.join(self.model_path, 'model.h5'))
self.__save_config()
plot(history)
return model
def train(self):
if self.attention:
model = self.__build_model()
else:
model = self.__build_model_no_attention()
checkpoint = ModelCheckpoint(os.path.join(self.model_path,
'weights.{epoch:03d}.h5'),
monitor='val_loss',
save_weights_only=True,
verbose=1,
save_best_only=True,
mode='min')
early = EarlyStopping(monitor="val_loss", mode="min", patience=10)
model_trained = model.fit(self.x_train,
self.y_train,
batch_size=128,
epochs=25,
validation_data=[self.x_test, self.y_test],
callbacks=[checkpoint, early])
plot(model_trained)
if self.attention:
model.save_weights(
os.path.join(self.model_path, 'final_model_weights.h5'))
else:
model.save_weights(
os.path.join(self.model_path,
'final_model_weights_no_attention.h5'))
self.__save_config()
return model
def train(self, batch_size=512, epochs=20):
model = self.build_model()
# early_stop配合checkpoint使用，可以得到val_loss最小的模型
early_stop = EarlyStopping(patience=3, verbose=1)
checkpoint = ModelCheckpoint(os.path.join(
self.model_path, 'weights.{epoch:03d}-{val_loss:.3f}.h5'),
verbose=1,
save_best_only=True)
history = model.fit(self.x_train,
self.y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
callbacks=[checkpoint, early_stop],
validation_data=(self.x_test, self.y_test))
plot(history)
return model
def train(self, x, y, test_size=0.2, batch_size=512, epochs=20):
model = self.build_model()
# early_stop配合checkpoint使用，可以得到val_loss最小的模型
early_stop = self.early_stop()
checkpoint = self.check_point()
x_train, x_val, y_train, y_val = train_test_split(x,
y,
test_size=test_size,
random_state=42)
history = model.fit(x_train,
y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
callbacks=[checkpoint, early_stop],
validation_data=(x_val, y_val))
plot(history)
return model
def train(self):
model = self.__build_model()
checkpoint = ModelCheckpoint(os.path.join(
self.model_path, 'weights.{epoch:03d}-{val_acc:.4f}.h5'),
monitor='val_acc',
verbose=1,
save_best_only=True,
mode='auto')
early_stop = EarlyStopping(patience=3, verbose=1)
history = model.fit(self.x_train,
self.y_train,
batch_size=self.batch_size,
epochs=self.epochs,
verbose=1,
callbacks=[checkpoint, early_stop],
validation_data=(self.x_test, self.y_test))
plot(history)
model.save(os.path.join(self.model_path, 'model.h5'))
self.__save_config()
return model
def train(self, weights_only=True, call_back=False):
model = self._build_model()
if call_back:
early_stopping = EarlyStopping(monitor='val_loss', patience=30)
stamp = 'lstm_%d' % self.n_hidden
checkpoint_dir = os.path.join(
self.model_path, 'checkpoints/' + str(int(time.time())) + '/')
if not os.path.exists(checkpoint_dir):
os.makedirs(checkpoint_dir)
bst_model_path = checkpoint_dir + stamp + '.h5'
if weights_only:
model_checkpoint = ModelCheckpoint(bst_model_path,
save_best_only=True,
save_weights_only=True)
else:
model_checkpoint = ModelCheckpoint(bst_model_path,
save_best_only=True)
tensor_board = TensorBoard(log_dir=checkpoint_dir +
"logs/{}".format(time.time()))
callbacks = [early_stopping, model_checkpoint, tensor_board]
else:
callbacks = None
model_trained = model.fit(
[self.x_train['left'], self.x_train['right']],
self.y_train,
batch_size=self.batch_size,
epochs=self.epochs,
validation_data=([self.x_val['left'],
self.x_val['right']], self.y_val),
verbose=1,
callbacks=callbacks)
if weights_only and not call_back:
model.save_weights(os.path.join(self.model_path,
'weights_only.h5'))
elif not weights_only and not call_back:
model.save(os.path.join(self.model_path, 'model.h5'))
self._save_config()
plot(model_trained)
return model