Keras LSTM-VAE(变分自动编码器)用于时间序列分析钼检测

Question

我正在尝试使用Keras为时间序列重建建模LSTM-VAE。

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。

我在训练网络时遇到了问题，在渴望执行模式下训练时出现了以下错误：

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

这里的输入形状是(7752,30,1)，30个时间步长和1个特征。

型号编码器：

# 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])

型号解码器：

# 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

有什么建议可以让这个模型发挥作用吗？

Answer 1

您需要在采样函数中推断batch_dim，并且需要注意您的损失。。。您的loss函数使用前几层的输出，因此需要注意这一点。我使用model.add_loss(...)实现了这一点

# 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')

这是正在运行的笔记本