LSTM用于回归

Question

问题：我有 s t timeSteps的序列和每个时间段包含 f them f 特征， （s x t x f）和s中的每个s用2个值（ target_1 和 target_2 ）

目标：型号/训练架构使用LSTM来学习/实现函数近似模型M并给定序列 s ，以预测 target_1 和 target_2 ？

这样的东西：

m （ s ）

下面的方法是可能无法使用的示例的KERAS实现。我为第一个目标值制作了2个模型，第二个目标值是1个。

model1 = Sequential()
model1.add(Masking(mask_value=-10.0))
model1.add(LSTM(1, input_shape=(batch, timesteps, features), return_sequences = True))  
model1.add(Flatten())
model1.add(Dense(hidden_units, activation = "relu"))
model1.add(Dense(1, activation = "linear"))
model1.compile(loss='mse', optimizer=Adam(learning_rate=0.0001))
model1.fit(x_train, y_train[:,0], validation_data=(x_test, y_test[:,0]), epochs=epochs, batch_size=batch, shuffle=False)

model2 = Sequential()
model2.add(Masking(mask_value=-10.0))
model2.add(LSTM(1, input_shape=(batch, timesteps, features), return_sequences=True))
model2.add(Flatten())
model2.add(Dense(hidden_units, activation = "relu"))
model2.add(Dense(1, activation = "linear"))
model2.compile(loss='mse', optimizer=Adam(learning_rate=0.0001))
model2.fit(x_train, y_train[:,1], validation_data=(x_test, y_test[:,1]), epochs=epochs, batch_size=batch, shuffle=False)

我想以某种方式充分利用LSTMS时间相关的内存，以实现良好的回归。

Answer 1

IIUC，您可以通过使用两个输出层从简单（天真的）方法开始：

import tensorflow as tf

timesteps, features = 20, 5
inputs = tf.keras.layers.Input((timesteps, features))
x = tf.keras.layers.Masking(mask_value=-10.0)(inputs)
x = tf.keras.layers.LSTM(32, return_sequences=False)(x)
x = tf.keras.layers.Dense(32, activation = "relu")(x)
output1 = Dense(1, activation = "linear", name='output1')(x)
output2 = Dense(1, activation = "linear", name='output2')(x)

model = tf.keras.Model(inputs, [output1, output2])
model.compile(loss='mse', optimizer=tf.keras.optimizers.Adam(learning_rate=0.0001))

x_train = tf.random.normal((500, timesteps, features))
y_train = tf.random.normal((500, 2))
model.fit(x_train, [y_train[:,0],y_train[:,1]] , epochs=5, batch_size=32, shuffle=False)