问题:我有S序列的T时间步长,每个时间步长都包含F特征,因此,总的来说(S x T x F(,并且S中的每个S由2个值描述(Target_1和Target_2(
目标:使用LSTM建模/训练体系结构,以学习/实现函数逼近器模型M,并给定序列s,以预测Target_1和Target_2?
类似这样的东西:
M(s(~(Target_1,Target_2
我真的很难找到一种方法,下面是一个可能不起作用的示例的Keras实现。我制作了两个模型——一个用于第一个目标值,一个用于第二个目标值。
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)
我想以某种方式很好地利用LSTM时间相关记忆,以实现良好的回归。
IIUC,您可以通过使用两个输出层从一个简单(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)