python - 时间序列的 seq2seq 预测

Question

我想制作一个 Seq2Seq 模型用于重建目的。我想要一个经过训练的模型来重建正常时间序列，并且假设这样的模型在重建训练期间没有看到异常时间序列时效果会很差。

我的代码和理解上都存在一些差距。我以此为方向，到目前为止已经做到了:traindata:input_data.shape(1000,60,1)和target_data.shape(1000,50,1)，目标数据是相同的训练数据，只是按照论文here中建议的相反顺序。用于推理:我想使用形状为 (3000,60,1) 的训练模型来预测另一个时间序列数据。现在有 2 点开放:如何指定训练模型的输入数据以及如何构建具有停止条件的推理部分？如有错误请指正。

from keras.models import Model
from keras.layers import Input
from keras.layers import LSTM
from keras.layers import Dense

num_encoder_tokens = 1#number of features
num_decoder_tokens = 1#number of features
encoder_seq_length = None
decoder_seq_length = None
batch_size = 50
epochs = 40

# same data for training 
input_seqs=()#shape (1000,60,1) with sliding windows
target_seqs=()#shape(1000,60,1) with sliding windows but reversed
x= #what has x to be ?

#data for inference 
# how do I specify the input data for my other time series ?

# Define training model
encoder_inputs = Input(shape=(encoder_seq_length,
                          num_encoder_tokens))
encoder = LSTM(128, return_state=True, return_sequences=True)
encoder_outputs = encoder(encoder_inputs)
_, encoder_states = encoder_outputs[0], encoder_outputs[1:]

decoder_inputs = Input(shape=(decoder_seq_length,
                          num_decoder_tokens))
decoder = LSTM(128, return_sequences=True)
decoder_outputs = decoder(decoder_inputs, initial_state=encoder_states)
decoder_outputs = TimeDistributed(
Dense(num_decoder_tokens, activation='tanh'))(decoder_outputs)
model = Model([encoder_inputs, decoder_inputs], decoder_outputs)

# Training
model.compile(optimizer='adam', loss='mse')
model.fit([input_seqs,x], target_seqs,
      batch_size=batch_size, epochs=epochs)


# Define sampling models for inference
encoder_model = Model(encoder_inputs, encoder_states)

decoder_state_input_h = Input(shape=(100,))
decoder_state_input_c = Input(shape=(100,))
decoder_states = [decoder_state_input_h, decoder_state_input_c]
decoder_outputs = decoder(decoder_inputs,
                      initial_state=decoder_states)
decoder_model = Model([decoder_inputs] + decoder_states,
decoder_outputs)

# Sampling loop for a batch of sequences
states_values = encoder_model.predict(input_seqs)
stop_condition = False
while not stop_condition:
    output_tokens = decoder_model.predict([target_seqs] + states_values)
#what else do I need to include here ? 
    break

Answer 1

def predict_sequence(infenc, infdec, source, n_steps, cardinality):
    # encode
    state = infenc.predict(source)
    # start of sequence input
    target_seq = array([0.0 for _ in range(cardinality)]).reshape(1, 1, cardinality)
    # collect predictions
    output = list()
    for t in range(n_steps):
        # predict next char
        yhat, h, c = infdec.predict([target_seq] + state)
        # store prediction
        output.append(yhat[0,0,:])
        # update state
        state = [h, c]
        # update target sequence
        target_seq = yhat
    return array(output)

您可以看到每个时间步的输出都从外部反馈到 LSTM 单元。