Autoencoder variationnel convolutionnel unidimensionnel dans keras

Question

J'essaie d'adapter this example from the git repo, fondamentalement en utilisant leur autre exemple de la même repo here (which uses deconvolution).

Je n'arrive pas à comprendre où je me trompe, mais il semble très basique. nous sommes ici:

import numpy as np 
import matplotlib.pyplot as plt 
from scipy.stats import norm 
# Keras uses TensforFlow backend as default 
from keras.layers import Input, Dense, Lambda, Flatten, Reshape 
from keras.layers import Conv1D,UpSampling1D 
from keras.models import Model 
from keras import backend as K 
from keras import metrics 
from keras.datasets import mnist 

# Input image dimensions 
steps, original_dim = 1, 28*28 # Take care here since we are changing this according to the data 
# Number of convolutional filters to use 
filters = 64 
# Convolution kernel size 
num_conv = 6 
# Set batch size 
batch_size = 100 
# Decoder output dimensionality 
decOutput = 10 

latent_dim = 20 
intermediate_dim = 256 
epsilon_std = 1.0 
epochs = 5 

x = Input(batch_shape=(batch_size,steps,original_dim)) 
# Play around with padding here, not sure what to go with. 
conv_1 = Conv1D(1, 
       kernel_size=num_conv, 
       padding='same', 
       activation='relu')(x) 
conv_2 = Conv1D(filters, 
       kernel_size=num_conv, 
       padding='same', 
       activation='relu', 
       strides=1)(conv_1) 
flat = Flatten()(conv_2) # Since we are passing flat data anyway, we probably don't need this. 
hidden = Dense(intermediate_dim, activation='relu')(flat) 
z_mean = Dense(latent_dim)(hidden) 
z_log_var = Dense(latent_dim)(hidden) 

def sampling(args): 
    z_mean, z_log_var = args 
    epsilon = K.random_normal(shape=(batch_size, latent_dim), 
           mean=0., stddev=epsilon_std) 
    return z_mean + K.exp(z_log_var) * epsilon # the original VAE divides z_log_var with two -- why? 

# note that "output_shape" isn't necessary with the TensorFlow backend 
# so you could write `Lambda(sampling)([z_mean, z_log_var])` 
z = Lambda(sampling, output_shape=(latent_dim,))([z_mean, z_log_var]) 



# we instantiate these layers separately so as to reuse them later 
decoder_h = Dense(intermediate_dim, activation='relu') 
decoder_mean = Dense(original_dim, activation='sigmoid') 

h_decoded = decoder_h(z) 
x_decoded_mean = decoder_mean(h_decoded) 

def vae_loss(x, x_decoded_mean): 
    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) # Double check wtf this is supposed to be 
    return xent_loss + kl_loss 

vae = Model(x, x_decoded_mean) 
vae.compile(optimizer='adam', loss=vae_loss) # 'rmsprop' 
vae.summary() 

qui sort comme:

____________________________________________________________________________________________________ 
Layer (type)      Output Shape   Param #  Connected to      
==================================================================================================== 
input_31 (InputLayer)   (100, 1, 784)   0            
____________________________________________________________________________________________________ 
conv1d_87 (Conv1D)    (100, 1, 1)   4705           
____________________________________________________________________________________________________ 
conv1d_88 (Conv1D)    (100, 1, 64)   448           
____________________________________________________________________________________________________ 
flatten_29 (Flatten)    (100, 64)    0            
____________________________________________________________________________________________________ 
dense_134 (Dense)    (100, 256)   16640           
____________________________________________________________________________________________________ 
dense_135 (Dense)    (100, 20)    5140           
____________________________________________________________________________________________________ 
dense_136 (Dense)    (100, 20)    5140           
____________________________________________________________________________________________________ 
lambda_24 (Lambda)    (100, 20)    0            
____________________________________________________________________________________________________ 
dense_137 (Dense)    (100, 256)   5376           
____________________________________________________________________________________________________ 
dense_138 (Dense)    (100, 784)   201488          
==================================================================================================== 
Total params: 238,937.0 
Trainable params: 238,937.0 
Non-trainable params: 0.0 

Ensuite, si je tente d'exécuter cela, comme si:

from keras.datasets import mnist 

img_rows, img_cols = 1,28*28 
original_img_size = (img_rows, img_cols) 

# train the VAE on MNIST digits 
(x_train, _), (x_test, y_test) = mnist.load_data() 

x_train = x_train.astype('float32')/255. 
x_train = x_train.reshape((x_train.shape[0],) + original_img_size) 

print('x_train.shape:', x_train.shape) 

N = 1000 
epochs = 2 
batch_size = int(N/10) 
vae.fit(x_train[0:N,:], x_train[0:N,:], 
     shuffle=True, 
     epochs=epochs, 
     batch_size=batch_size) 

Je reçois cette erreur, mais je ne peux pas tout à fait comprendre comment le dépasser. Il a quelque chose à aller avec de Conv1D à Dense ...

ValueError: Cannot feed value of shape (100, 1, 784) for Tensor u'dense_138_target:0', which has shape '(?, ?)' 

Answer 1

Essayez remodelant x_decoded_mean à votre forme d'entrée depuis x_train[0:N,:] est en forme (1,784) mais votre sortie est (784,) quelque chose comme

x_decoded_mean = Reshape([1,784])(x_decoded_mean)