用于时间序列异常检测的 Keras LSTM-VAE(变分自动编码器)

问题描述

我正在尝试使用 Keras 为 LSTM-VAE 建模以进行时间序列重建.

I am trying to model LSTM-VAE for time series reconstruction using Keras.

我曾提到 https://github.com/twairball/keras_lstm_vae/blob/master/lstm_vae/vae.py 和 https://machinelearningmastery.com/lstm-autoencoders/ 用于创建 LSTM-VAE 架构.

I had referred to https://github.com/twairball/keras_lstm_vae/blob/master/lstm_vae/vae.py and https://machinelearningmastery.com/lstm-autoencoders/ for creating the LSTM-VAE architecture.

我在训练网络时遇到了问题，在 Eager Execution 模式下训练时出现以下错误:

I have trouble training the network, I get the following error while training in eager execution mode:

  InvalidArgumentError: Incompatible shapes: [8,1] vs. [32,1] [Op:Mul]

输入形状是 (7752,30,1) 这里有 30 个时间步和 1 个特征.

Input shape is (7752,30,1) here 30 time steps and 1 feature.

模型编码器:

# encoder
latent_dim = 1
inter_dim = 32

#sample,timesteps, features
input_x = keras.layers.Input(shape= (X_train.shape[1], X_train.shape[2]))

#intermediate dimension
h = keras.layers.LSTM(inter_dim)(input_x)

#z_layer
z_mean = keras.layers.Dense(latent_dim)(h)
z_log_sigma = keras.layers.Dense(latent_dim)(h)
z = Lambda(sampling)([z_mean, z_log_sigma])

模型解码器:

# Reconstruction decoder
decoder1 = RepeatVector(X_train.shape[1])(z)
decoder1 = keras.layers.LSTM(100, activation='relu', return_sequences=True)(decoder1)
decoder1 = keras.layers.TimeDistributed(Dense(1))(decoder1)

采样功能:

batch_size = 32
def sampling(args):
    z_mean, z_log_sigma = args
    epsilon = K.random_normal(shape=(batch_size, latent_dim),mean=0., stddev=1.)
    return z_mean + z_log_sigma * epsilon

VAE 损失函数:

def vae_loss2(input_x, decoder1):
    """ Calculate loss = reconstruction loss + KL loss for each data in minibatch """
    # E[log P(X|z)]
    recon = K.sum(K.binary_crossentropy(input_x, decoder1), axis=1)
    # D_KL(Q(z|X) || P(z|X)); calculate in closed form as both dist. are Gaussian
    kl = 0.5 * K.sum(K.exp(z_log_sigma) + K.square(z_mean) - 1. - z_log_sigma, axis=1)

    return recon + kl

LSTM-VAE 模型架构

有什么建议可以使模型工作吗?

Any suggestions to make the model work?

推荐答案

你需要在采样函数中推断batch_dim，你需要注意你的损失......你的损失函数使用了之前层的输出，所以你需要照顾这个.我使用 model.add_loss(...)

you need to infer the batch_dim inside the sampling function and you need to pay attention to your loss... your loss function uses the output of previous layers so you need to take care of this. I implement this using model.add_loss(...)

# encoder
latent_dim = 1
inter_dim = 32
timesteps, features = 100, 1

def sampling(args):
    z_mean, z_log_sigma = args
    batch_size = tf.shape(z_mean)[0] # <================
    epsilon = K.random_normal(shape=(batch_size, latent_dim), mean=0., stddev=1.)
    return z_mean + z_log_sigma * epsilon

# timesteps, features
input_x = Input(shape= (timesteps, features))

#intermediate dimension
h = LSTM(inter_dim, activation='relu')(input_x)

#z_layer
z_mean = Dense(latent_dim)(h)
z_log_sigma = Dense(latent_dim)(h)
z = Lambda(sampling)([z_mean, z_log_sigma])

# Reconstruction decoder
decoder1 = RepeatVector(timesteps)(z)
decoder1 = LSTM(inter_dim, activation='relu', return_sequences=True)(decoder1)
decoder1 = TimeDistributed(Dense(features))(decoder1)

def vae_loss2(input_x, decoder1, z_log_sigma, z_mean):
    """ Calculate loss = reconstruction loss + KL loss for each data in minibatch """
    # E[log P(X|z)]
    recon = K.sum(K.binary_crossentropy(input_x, decoder1))
    # D_KL(Q(z|X) || P(z|X)); calculate in closed form as both dist. are Gaussian
    kl = 0.5 * K.sum(K.exp(z_log_sigma) + K.square(z_mean) - 1. - z_log_sigma)

    return recon + kl

m = Model(input_x, decoder1)
m.add_loss(vae_loss2(input_x, decoder1, z_log_sigma, z_mean)) #<===========
m.compile(loss=None, optimizer='adam')

这里是正在运行的笔记本

这篇关于用于时间序列异常检测的 Keras LSTM-VAE(变分自动编码器)的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！