首页 文章

Python / Keras / Theano错误的自动编码器维度

提问于
浏览 次
8

我正在尝试关注Deep Autoencoder Keras example . 我'm getting a dimension mismatch exception, but for the life of me, I can'弄清楚原因 . 当我只使用一个编码维度时它可以工作，但是当我堆叠它们时却不行 .

例外：输入0与图层dense_18不兼容：预期shape =（None，128），found shape =（None，32）*

错误在行 decoder = Model(input=encoded_input, output=decoder_layer(encoded_input))

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

import numpy as np

# this is the size of the encoded representations
encoding_dim = 32

#NPUT LAYER
input_img = Input(shape=(784,))

#ENCODE LAYER
# "encoded" is the encoded representation of the input
encoded = Dense(encoding_dim*4, activation='relu')(input_img)
encoded = Dense(encoding_dim*2, activation='relu')(encoded)
encoded = Dense(encoding_dim, activation='relu')(encoded)

#DECODED LAYER
# "decoded" is the lossy reconstruction of the input
decoded = Dense(encoding_dim*2, activation='relu')(encoded)
decoded = Dense(encoding_dim*4, activation='relu')(decoded)
decoded = Dense(784, activation='sigmoid')(decoded)

#MODEL
autoencoder = Model(input=input_img, output=decoded)


#SEPERATE ENCODER MODEL
encoder = Model(input=input_img, output=encoded)

# create a placeholder for an encoded (32-dimensional) input
encoded_input = Input(shape=(encoding_dim,))

# retrieve the last layer of the autoencoder model
decoder_layer = autoencoder.layers[-1]

# create the decoder model
decoder = Model(input=encoded_input, output=decoder_layer(encoded_input))

#COMPILER
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')
machine-learning neural-network theano keras autoencoder

3 回答

  • -1

    感谢Marcin的暗示 . 原来需要展开所有解码器层以使其工作 .

    # retrieve the last layer of the autoencoder model
decoder_layer1 = autoencoder.layers[-3]
decoder_layer2 = autoencoder.layers[-2]
decoder_layer3 = autoencoder.layers[-1]

# create the decoder model
decoder = Model(input=encoded_input, output=decoder_layer3(decoder_layer2(decoder_layer1(encoded_input))))
    回复于
  • 8

    问题在于：

    # retrieve the last layer of the autoencoder model
decoder_layer = autoencoder.layers[-1]

    在以前的模型中 - 最后一层是唯一的解码器层 . 所以它输入也是解码器的输入 . 但是现在你有3个解码层，所以你必须回到第一个才能获得解码器的第一层 . 所以改变这一行：

    # retrieve the last layer of the autoencoder model
decoder_layer = autoencoder.layers[-3]

    应该做的工作 .

    回复于
  • 2

    您需要将每个解码器层的转换应用到前一个解码器层 . 您可以在接受的答案中手动展开和硬编码这些，或者以下循环应该处理它：

    # create a placeholder for an encoded (32-dimensional) input
encoded_input = Input(shape=(encoding_dim,))

# retrieve the decoder layers and apply to each prev layer
num_decoder_layers = 3
decoder_layer = encoded_input
for i in range(-num_decoder_layers, 0):
    decoder_layer = autoencoder.layers[i](decoder_layer)

# create the decoder model
decoder = Model(encoded_input, decoder_layer)
    回复于

相关问题