python - 解决自动编码器模型制作过程中的图形断开错误

Question

我有一个简单的卷积网络(自动编码器)，我想将我的模型分为编码器和解码器两部分。在编码器和解码器之间，我将随机图像添加到编码器的输出，然后将结果发送到解码器部分，但是当我想从编码器到解码器创建模型时，它会产生以下错误:

ValueError: Graph disconnected: cannot obtain value for tensor Tensor("input_2:0", shape=(?, 28, 28, 1), dtype=float32) at layer "input_2". The following previous layers were accessed without issue: []

当我想要创建解码器模型时，产生了这个错误。我无法理解为什么会产生这个错误。请帮我解决这个错误。

from keras.layers import Input, Concatenate, GaussianNoise,Dropout
from keras.layers import Conv2D
from keras.models import Model
from keras.datasets import mnist
from keras.callbacks import TensorBoard
from keras import backend as K
from keras import layers
import matplotlib.pyplot as plt
import tensorflow as tf
import keras as Kr
import numpy as np
import pylab as pl
import matplotlib.cm as cm

#-----------------building w train---------------------------------------------
w_main = np.random.randint(2,size=(1,4,4,1))
w_main=w_main.astype(np.float32)
w_expand=np.zeros((1,28,28,1),dtype='float32')
w_expand[:,0:4,0:4]=w_main
w_expand.reshape(1,28,28,1)
w_expand=np.repeat(w_expand,49999,0)

#-----------------building w validation---------------------------------------------
w_valid = np.random.randint(2,size=(1,4,4,1))
w_valid=w_valid.astype(np.float32)
wv_expand=np.zeros((1,28,28,1),dtype='float32')
wv_expand[:,0:4,0:4]=w_valid
wv_expand.reshape(1,28,28,1)
wv_expand=np.repeat(wv_expand,9999,0)

#-----------------building w test---------------------------------------------
w_test = np.random.randint(2,size=(1,4,4,1))
w_test=w_test.astype(np.float32)
wt_expand=np.zeros((1,28,28,1),dtype='float32')
wt_expand[:,0:4,0:4]=w_test
wt_expand.reshape(1,28,28,1)
wt_expand=np.repeat(wt_expand,10000,0)

#-----------------------encoder------------------------------------------------
#------------------------------------------------------------------------------
wtm=Input((28,28,1))
image = Input((28, 28, 1))
conv1 = Conv2D(16, (3, 3), activation='relu', padding='same', name='convl1e')(image)
conv2 = Conv2D(32, (3, 3), activation='relu', padding='same', name='convl2e')(conv1)
conv3 = Conv2D(8, (3, 3), activation='relu', padding='same', name='convl3e')(conv2)
DrO1=Dropout(0.25)(conv3)
encoded =  Conv2D(1, (3, 3), activation='relu', padding='same',name='reconstructed_I')(DrO1)


#-----------------------adding w---------------------------------------
#add_const = Kr.layers.Lambda(lambda x: x + Kr.backend.constant(w_expand))
#encoded_merged=Kr.layers.Add()([encoded,wtm])

add_const = Kr.layers.Lambda(lambda x: x + wtm)
encoded_merged = add_const(encoded)

encoder=Model(inputs=image, outputs=encoded_merged)
encoder.summary()

#-----------------------decoder------------------------------------------------
#------------------------------------------------------------------------------

#encoded_merged = Input((28, 28, 2))
deconv1 = Conv2D(16, (3, 3), activation='relu', padding='same', name='convl1d')(encoded_merged)
deconv2 = Conv2D(32, (3, 3), activation='relu', padding='same', name='convl2d')(deconv1)
deconv3 = Conv2D(8, (3, 3), activation='relu',padding='same', name='convl3d')(deconv2)
DrO2=Dropout(0.25)(deconv3)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same', name='decoder_output')(DrO2) 

decoder=Model(inputs=encoded_merged, outputs=decoded)
#decoder.summary()

新代码:

from keras.layers import Input, Concatenate, GaussianNoise,Dropout
from keras.layers import Conv2D
from keras.models import Model
from keras.datasets import mnist
from keras.callbacks import TensorBoard
from keras import backend as K
from keras import layers
import matplotlib.pyplot as plt
import tensorflow as tf
import keras as Kr
import numpy as np
import pylab as pl
import matplotlib.cm as cm
import keract
from keras import optimizers
from keras import regularizers
from keras.callbacks import EarlyStopping

from tensorflow.python.keras.layers import Lambda;

#-----------------building w train---------------------------------------------
w_main = np.random.randint(2,size=(1,14,14,1))
w_main=w_main.astype(np.float32)
w_expand=np.zeros((1,28,28,1),dtype='float32')
w_expand[:,0:14,0:14]=w_main
w_expand.reshape(1,28,28,1)
w_expand=np.repeat(w_expand,49999,0)

#-----------------building w validation---------------------------------------------
w_valid = np.random.randint(2,size=(1,14,14,1))
w_valid=w_valid.astype(np.float32)
wv_expand=np.zeros((1,28,28,1),dtype='float32')
wv_expand[:,0:14,0:14]=w_valid
wv_expand.reshape(1,28,28,1)
wv_expand=np.repeat(wv_expand,9999,0)

#-----------------building w test---------------------------------------------
w_test = np.random.randint(2,size=(1,14,14,1))
w_test=w_test.astype(np.float32)
wt_expand=np.zeros((1,28,28,1),dtype='float32')
wt_expand[:,0:14,0:14]=w_test
wt_expand.reshape(1,28,28,1)
#wt_expand=np.repeat(wt_expand,10000,0)

#-----------------------encoder------------------------------------------------
#------------------------------------------------------------------------------
wtm=Input((28,28,1))
image = Input((28, 28, 1))
conv1 = Conv2D(16, (3, 3), activation='relu', padding='same', name='convl1e')(image)
conv2 = Conv2D(32, (3, 3), activation='relu', padding='same', name='convl2e')(conv1)
conv3 = Conv2D(8, (3, 3), activation='relu', padding='same', name='convl3e')(conv2)
#conv3 = Conv2D(8, (3, 3), activation='relu', padding='same', name='convl3e', kernel_initializer='Orthogonal',bias_initializer='glorot_uniform')(conv2)
DrO1=Dropout(0.25)(conv3)
encoded =  Conv2D(1, (3, 3), activation='relu', padding='same',name='reconstructed_I')(DrO1)


#-----------------------adding watermark---------------------------------------
#add_const = Kr.layers.Lambda(lambda x: x + Kr.backend.constant(w_expand))
#encoded_merged=Kr.layers.Add()([encoded,wtm])

add_const = Kr.layers.Lambda(lambda x: x[0] + x[1])
encoded_merged = add_const([encoded,wtm])
encoder=Model(inputs=[image,wtm], outputs= encoded_merged)
encoder.summary()

#-----------------------decoder------------------------------------------------
#------------------------------------------------------------------------------
deconv_input=Input((28,28,1))
#encoded_merged = Input((28, 28, 2))
deconv1 = Conv2D(16, (3, 3), activation='relu', padding='same', name='convl1d',kernel_regularizer=regularizers.l2(0.001), kernel_initializer='Orthogonal')(deconv_input)
deconv2 = Conv2D(32, (3, 3), activation='relu', padding='same', name='convl2d')(deconv1)
deconv3 = Conv2D(8, (3, 3), activation='relu',padding='same', name='convl3d')(deconv2)
DrO2=Dropout(0.25)(deconv3)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same', name='decoder_output')(DrO2) 

decoder=Model(inputs=deconv_input, outputs=decoded)
#decoder.summary()
encoded_merged = encoder([image,wtm])
decoded = decoder(encoded_merged)

model=Model(inputs=[image,wtm],outputs=decoded)
#----------------------w extraction------------------------------------
convw1 = Conv2D(16, (3,3), activation='relu', padding='same', name='conl1w',kernel_regularizer=regularizers.l2(0.001), kernel_initializer='Orthogonal')(decoded)
convw2 = Conv2D(32, (3, 3), activation='relu', padding='same', name='convl2w')(convw1)
convw3 = Conv2D(8, (3, 3), activation='relu', padding='same', name='conl3w')(convw2)
DrO3=Dropout(0.25)(convw3)
pred_w = Conv2D(1, (1, 1), activation='sigmoid', padding='same', name='reconstructed_W')(DrO3)  
# reconsider activation (is W positive?)
# should be filter=1 to match W
watermark_extraction=Model(inputs=[image,wtm],outputs=[decoded,pred_w])


#----------------------training the model--------------------------------------
#------------------------------------------------------------------------------
#----------------------Data preparesion----------------------------------------

(x_train, _), (x_test, _) = mnist.load_data()
x_validation=x_train[1:10000,:,:]
x_train=x_train[10001:60000,:,:]
#
x_train = x_train.astype('float32') / 255.
x_test = x_test.astype('float32') / 255.
x_validation = x_validation.astype('float32') / 255.
x_train = np.reshape(x_train, (len(x_train), 28, 28, 1))  # adapt this if using `channels_first` image data format
x_test = np.reshape(x_test, (len(x_test), 28, 28, 1))  # adapt this if using `channels_first` image data format
x_validation = np.reshape(x_validation, (len(x_validation), 28, 28, 1))

#---------------------compile and train the model------------------------------
# is accuracy sensible metric for this model?
adadelta=optimizers.Adadelta(lr=1.0,decay=1/1000)
watermark_extraction.compile(optimizer=adadelta, loss={'decoder_output':'mse','reconstructed_W':'mse'}, metrics=['mae'])
watermark_extraction.fit([x_train,w_expand], [x_train,w_expand],
          epochs=10,
          batch_size=32, 
          validation_data=([x_validation,wv_expand], [x_validation,wv_expand]),
          callbacks=[TensorBoard(log_dir='E:/tmp/AutewithW200', histogram_freq=0, write_graph=False),EarlyStopping(monitor='val_loss', patience=10,min_delta=0)])
model.summary()

新错误:

ValueError: Unknown entry in loss dictionary: "decoder_output". Only expected the following keys: ['model_14', 'reconstructed_W']

Answer 1

当您将张量放入公式中而不是将张量传递到层时，Lambda 层正在攻击系统。

add_const = Kr.layers.Lambda(lambda x: x[0] + x[1])
encoded_merged = add_const([encoded,wtm])

或者简单地说:

encoded_merged = Add()([encoded,wtm])

您必须使 wtm 成为模型的输入:

encoder = Model(inputs=[image,wtm], outputs = encoded_merged)

<小时/>

模型应该从输入张量开始，而不是从图中间的张量开始:

deconv_inputs = Input(shape_of_encoded_merged)
deconv1 =  Conv2D(16, (3, 3), activation='relu', padding='same', name='convl1d')(deconv_inputs)
....

decoder = Model(inputs=deconv_inputs, outputs=decoded)

<小时/>

然后您可以创建自动编码器:

wtm=Input((28,28,1))
image = Input((28, 28, 1))    

encoded_merged = encoder([image,wtm])
decoded = decoder(encoded_merged)

autoencoder = Model([image,wtm], decoded)