我尝试使用 LSTM 运行变分自动编码器。所以我用LSTM层替换了dense层。但它不起作用。这是一个例子：
# generate data
data = generate_example(length = 560,seed=253)
normal_data = data[1:400,:]
fault_data = data[400:,:]
timesteps = 5
# data prepare
# define the normalize function
# normalize function
def normalize(normal, fault):
normal_mean = normal.mean(axis = 0)
normal_std = normal.std(axis = 0)
# normalize
fault_normalize = np.array(fault).reshape(fault.shape)
for i in np.linspace(0,fault.shape[1]-1):
i = int(i)
fault_normalize[:,i] = (fault[:,i] - normal_mean[i])/normal_std[i]
return(fault_normalize)
# define the lag function
# lag function
def lag(data, timesteps = 10):
# define the shape of return data
data_row = data.shape[0]
data_col = data.shape[1]
data_len = data_row - timesteps
data_lag = np.repeat(0,data_len*timesteps*data_col).reshape(data_len,timesteps,data_col).astype("float")
for i in np.arange(0,data_len):
data_lag[i,:,:] = data[i:(i+timesteps),:]
return(data_lag)
normal_scale = normalize(normal = normal_data, fault = normal_data)
normal_scale = lag(data=normal_scale, timesteps = timesteps)
这是变分自动编码器
from __future__ import print_function
import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import norm
from keras.layers import Input, Dense, Lambda, LSTM, RepeatVector, TimeDistributed
from keras.models import Model
from keras import backend as K
from keras import metrics
from keras.datasets import mnist
batch_size = 100
original_dim = 3
latent_dim = 2
intermediate_dim = 5
epochs = 100
epsilon_std = 1.0
x = Input(shape=(timesteps,original_dim))
h = LSTM(intermediate_dim,return_sequences=False)(x)
z_mean = Dense(latent_dim)(h)
z_log_var = Dense(latent_dim)(h)
def sampling(args):
z_mean, z_log_var = args
epsilon = K.random_normal(shape=(K.shape(z_mean)[0], latent_dim), mean=0.,
stddev=epsilon_std)
return z_mean + K.exp(z_log_var / 2) * epsilon
# note that "output_shape" isn't necessary with the TensorFlow backend
z = Lambda(sampling, output_shape=(latent_dim,))([z_mean, z_log_var])
# we instantiate these layers separately so as to reuse them later
decoded_repeat = RepeatVector(timesteps)
decoder_h = LSTM(intermediate_dim, activation='tanh',return_sequences=True)
decoder_mean = TimeDistributed(Dense(original_dim, activation='sigmoid'))
h_repeat = decoded_repeat(z)
h_decoded = decoder_h(h_repeat)
x_decoded_mean = decoder_mean(h_decoded)
# instantiate VAE model
vae = Model(x, x_decoded_mean)
# Compute VAE loss
xent_loss = original_dim * metrics.binary_crossentropy(x, x_decoded_mean)
kl_loss = - 0.5 * K.sum(1 + z_log_var - K.square(z_mean) - K.exp(z_log_var), axis=-1)
vae_loss = K.mean(xent_loss + kl_loss)
vae.add_loss(vae_loss)
vae.compile(optimizer='rmsprop',loss=None)
vae.summary()
x_train = normal_scale
x_test = normal_scale
vae.fit(x_train,
shuffle=True,
epochs=epochs,
batch_size=batch_size)
# build a model to project inputs on the latent space
encoder = Model(x, z_mean)
但是我InvalidArgumentError: Incompatible shapes: [100,5] vs. [100]得到了错误，我不认为有不兼容的形状。这是变分自动编码器的结构
____________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
====================================================================================================
input_76 (InputLayer) (None, 5, 3) 0
____________________________________________________________________________________________________
lstm_42 (LSTM) (None, 5) 180 input_76[0][0]
____________________________________________________________________________________________________
dense_317 (Dense) (None, 2) 12 lstm_42[0][0]
____________________________________________________________________________________________________
dense_318 (Dense) (None, 2) 12 lstm_42[0][0]
____________________________________________________________________________________________________
lambda_72 (Lambda) (None, 2) 0 dense_317[0][0]
dense_318[0][0]
____________________________________________________________________________________________________
repeat_vector_20 (RepeatVector) (None, 5, 2) 0 lambda_72[0][0]
____________________________________________________________________________________________________
lstm_43 (LSTM) (None, 5, 5) 160 repeat_vector_20[0][0]
____________________________________________________________________________________________________
time_distributed_18 (TimeDistrib (None, 5, 3) 18 lstm_43[0][0]
====================================================================================================
Total params: 382
Trainable params: 382
Non-trainable params: 0
错误发生在损失函数的计算中：
vae_loss = K.mean(xent_loss + kl_loss)
这里，xent_loss是一个形状为(100, 5)的张量，而kl_loss的张量形状为(100,)。扩展kl_loss的维度将启用广播(我强调这就是您的意图(：
vae_loss = K.mean(xent_loss + kl_loss[:, None])