如何解决如何与张量流交叉验证?
如何与张量流交叉验证?以及如何优化以改进多变量回归模型)),但是交叉验证中的主要问题是
# Создаем последовательную модель
model = Sequential()
# Добавляем уровни сети
model.add(Dense(2048,input_dim=trainInput.shape[1],activation="relu"))
model.add(Dense(2048,activation="relu"))
model.add(Dense(1024,activation="relu"))
model.add(layers.Dropout(0.1))
model.add(Dense(1))
# Компилируем сеть и задаем оптимизатор
optimizer = tf.keras.optimizers.Adam(learning_rate=0.0008)
model.compile(loss='mse',optimizer=optimizer,metrics=["mse","mae"])
#print(model.summary())
class PrintDot(keras.callbacks.Callback):
def on_epoch_end(self,epoch,logs):
if epoch % 10 == 0: print('')
print('.',end='')
EPOCHS = 50
BATCH = 30
early_stop = keras.callbacks.EarlyStopping(monitor='val_loss',patience = 3)
history = model.fit(
trainInput,trainTarget,batch_size = BATCH,epochs=EPOCHS,validation_data=(validationInput,validationTarget),verbose = 0,callbacks=[early_stop,PrintDot()])
# Вывод истории обучения
hist = pd.DataFrame(history.history)
hist['epoch'] = history.epoch
hist
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。