当我想将整个网络分成两个模型时，为什么在 Keras 中会发生此错误，“Graph disconnected”？

Question

我在 keras 中有一个自动编码器，我需要为每个部分定义一个不同的模型，因为我的网络有两个输出，我希望在测试期间为每个输出有两个单独的网络，但是当我这样做时，它会产生以下结果错误。

Traceback（最近一次调用最后一次）：

文件“”，第 99 行，在 wext=Model(inputs=decoded_noise,outputs=pred_w)

文件 "D:\software\Anaconda3\envs\py36\lib\site-packages\keras\legacy\interfaces.py", 第 91 行，在包装器中 返回函数(*args, **kwargs)

文件 "D:\software\Anaconda3\envs\py36\lib\site-packages\keras\engine\network.py", 第 93 行，在 init 中 self._init_graph_network(*args, **kwargs)

文件 "D:\software\Anaconda3\envs\py36\lib\site-packages\keras\engine\network.py", 第 231 行，在 _init_graph_network self.inputs, self.outputs)

文件 "D:\software\Anaconda3\envs\py36\lib\site-packages\keras\engine\network.py", 第 1443 行，在 _map_graph_network str(layers_with_complete_input))

ValueError: Graph disconnected: cannot get value for tensor Tensor("input_8:0", shape=(?, 28, 28, 1), dtype=float32) 在层 “输入_8”。访问以下先前层没有问题： []

我希望在测试期间有两个网络，其中一个从编码器到解码器末端，第二个用于 w 提取部分。问题是什么？谢谢你。

#-----------------------encoder------------------------------------------------
wtm=Input((28,28,1))
image = Input((28, 28, 1))
conv1 = Conv2D(64, (5, 5), activation='relu', padding='same', name='convl1e',dilation_rate=(2,2))(image)
conv2 = Conv2D(64, (5, 5), activation='relu', padding='same', name='convl2e',dilation_rate=(2,2))(conv1)
conv3 = Conv2D(64, (5, 5), activation='relu', padding='same', name='convl3e',dilation_rate=(2,2))(conv2)
BN=BatchNormalization()(conv3)
encoded =  Conv2D(1, (5, 5), activation='relu', padding='same',name='encoded_I',dilation_rate=(2,2))(BN)


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

#-----------------------decoder------------------------------------------------
deconv1 = Conv2D(64, (5, 5), activation='relu', padding='same', name='convl1d',dilation_rate=(2,2))(encoded_merged)
deconv2 = Conv2D(64, (5, 5), activation='relu', padding='same', name='convl2d',dilation_rate=(2,2))(deconv1)
deconv3 = Conv2D(64, (5, 5), activation='relu',padding='same', name='convl3d',dilation_rate=(2,2))(deconv2)
deconv4 = Conv2D(64, (5, 5), activation='relu',padding='same', name='convl4d',dilation_rate=(2,2))(deconv3)
BNd=BatchNormalization()(deconv3)

decoded = Conv2D(1, (5, 5), activation='sigmoid', padding='same', name='decoder_output',dilation_rate=(2,2))(BNd) 

model1=Model(inputs=[image,wtm],outputs=decoded)

decoded_noise = GaussianNoise(0.5)(decoded)

#----------------------w extraction------------------------------------
convw1 = Conv2D(64, (3,3), activation='relu', padding='same', name='conl1w',dilation_rate=(2,2))(decoded_noise)
convw2 = Conv2D(64, (3, 3), activation='relu', padding='same', name='convl2w',dilation_rate=(2,2))(convw1)
convw3 = Conv2D(64, (3, 3), activation='relu', padding='same', name='conl3w',dilation_rate=(2,2))(convw2)
convw4 = Conv2D(64, (3, 3), activation='relu', padding='same', name='conl4w',dilation_rate=(2,2))(convw3)
convw5 = Conv2D(64, (3, 3), activation='relu', padding='same', name='conl5w',dilation_rate=(2,2))(convw4)
convw6 = Conv2D(64, (3, 3), activation='relu', padding='same', name='conl6w',dilation_rate=(2,2))(convw5)
pred_w = Conv2D(1, (1, 1), activation='sigmoid', padding='same', name='reconstructed_W',dilation_rate=(2,2))(convw6)  
wext=Model(inputs=decoded_noise,outputs=pred_w)
final=Model(inputs=[image,wtm],outputs=[decoded,pred_w])

修改后的代码：

from keras.layers import Input, Concatenate, GaussianNoise,Cropping2D,Activation,Dropout,BatchNormalization,MaxPool2D,AveragePooling2D,ZeroPadding2D
from keras.layers import Conv2D, AtrousConv2D
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
from keras.optimizers import SGD,RMSprop,Adam
from keras.callbacks import ReduceLROnPlateau
from keras.callbacks import EarlyStopping
from keras.callbacks import ModelCheckpoint
import numpy as np
import pylab as pl
import matplotlib.cm as cm
import keract
from matplotlib import pyplot
from keras import optimizers
from keras import regularizers

from tensorflow.python.keras.layers import Lambda;
w_expand=np.zeros((49999,28,28),dtype='float32')
wv_expand=np.zeros((9999,28,28),dtype='float32')
wt_random=np.random.randint(2, size=(49999,4,4))
wt_random=wt_random.astype(np.float32)
wv_random=np.random.randint(2, size=(9999,4,4))
wv_random=wv_random.astype(np.float32)
w_expand[:,:4,:4]=wt_random
wv_expand[:,:4,:4]=wv_random
x,y,z=w_expand.shape
w_expand=w_expand.reshape((x,y,z,1))
x,y,z=wv_expand.shape
wv_expand=wv_expand.reshape((x,y,z,1))

#-----------------building w test---------------------------------------------
w_test = np.random.randint(2,size=(1,4,4))
w_test=w_test.astype(np.float32)
wt_expand=np.zeros((1,28,28),dtype='float32')
wt_expand[:,0:4,0:4]=w_test
wt_expand=wt_expand.reshape((1,28,28,1))
#-----------------------encoder------------------------------------------------
#------------------------------------------------------------------------------
wtm=Input((28,28,1))
image = Input((28, 28, 1))
conv1 = Conv2D(64, (5, 5), activation='relu', padding='same', name='convl1e',dilation_rate=(2,2))(image)
conv2 = Conv2D(64, (5, 5), activation='relu', padding='same', name='convl2e',dilation_rate=(2,2))(conv1)
conv3 = Conv2D(64, (5, 5), activation='relu', padding='same', name='convl3e',dilation_rate=(2,2))(conv2)
BN=BatchNormalization()(conv3)
encoded =  Conv2D(1, (5, 5), activation='relu', padding='same',name='encoded_I',dilation_rate=(2,2))(BN)


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

#-----------------------decoder------------------------------------------------
deconv1 = Conv2D(64, (5, 5), activation='relu', padding='same', name='convl1d',dilation_rate=(2,2))(encoded_merged)
deconv2 = Conv2D(64, (5, 5), activation='relu', padding='same', name='convl2d',dilation_rate=(2,2))(deconv1)
deconv3 = Conv2D(64, (5, 5), activation='relu',padding='same', name='convl3d',dilation_rate=(2,2))(deconv2)
deconv4 = Conv2D(64, (5, 5), activation='relu',padding='same', name='convl4d',dilation_rate=(2,2))(deconv3)
BNd=BatchNormalization()(deconv3)

decoded = Conv2D(1, (5, 5), activation='sigmoid', padding='same', name='decoder_output',dilation_rate=(2,2))(BNd) 

model1=Model(inputs=[image,wtm],outputs=decoded)
decoded_input=Input((28,28,1))

#----------------------w extraction------------------------------------
convw1 = Conv2D(64, (3,3), activation='relu', padding='same', name='conl1w',dilation_rate=(2,2))(decoded_input)
convw2 = Conv2D(64, (3, 3), activation='relu', padding='same', name='convl2w',dilation_rate=(2,2))(convw1)
convw3 = Conv2D(64, (3, 3), activation='relu', padding='same', name='conl3w',dilation_rate=(2,2))(convw2)
convw4 = Conv2D(64, (3, 3), activation='relu', padding='same', name='conl4w',dilation_rate=(2,2))(convw3)
convw5 = Conv2D(64, (3, 3), activation='relu', padding='same', name='conl5w',dilation_rate=(2,2))(convw4)
convw6 = Conv2D(64, (3, 3), activation='relu', padding='same', name='conl6w',dilation_rate=(2,2))(convw5)
pred_w = Conv2D(1, (1, 1), activation='sigmoid', padding='same', name='reconstructed_W',dilation_rate=(2,2))(convw6)  
decoded_noise = GaussianNoise(0.5)(decoded)
wext=Model(inputs=decoded_input, outputs=pred_w)
pred_w = wext(decoded_noise)

w_extraction=Model(inputs=[image,wtm],outputs=[decoded,pred_w])
#----------------------training the model-----------------------------------

(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------------------------------
opt=SGD(momentum=0.99,lr=0.0001)
w_extraction.compile(optimizer='adam', loss={'imageprim':'mse','wprimmain':'binary_crossentropy'}, loss_weights={'imageprim': 1.0, 'wprimmain': 1.0},metrics=['mae'])
es = EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=40)
#rlrp = ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=20, min_delta=1E-4, verbose=1)
mc = ModelCheckpoint('los4x4_con_tile_convolw_FBN_SigAct_SandPAttack.h5', monitor='val_loss', mode='min', verbose=1, save_best_only=True)
history=w_extraction.fit([x_train,w_expand], [x_train,w_expand],
          epochs=1,
          batch_size=32, 
          validation_data=([x_validation,wv_expand], [x_validation,wv_expand]),
          callbacks=[TensorBoard(log_dir='/home/jamalm8/tensorboardGNWLoss/', histogram_freq=0, write_graph=False),es,mc])
w_extraction.summary()

产生的错误：

Traceback（最近一次调用最后一次）：

文件“”，第 113 行，在 w_extraction.compile(optimizer='adam', loss={'imageprim':'mse','wprimmain':'binary_crossentropy'}, loss_weights={'imageprim': 1.0, 'wprimmain': 1.0},metrics=['mae'])

文件 "D:\software\Anaconda3\envs\py36\lib\site-packages\keras\engine\training.py", 第 119 行，在编译中 str(self.output_names))

ValueError：损失字典中的未知条目：“imageprim”。仅有的 预期以下键：['decoder_output', 'model_29']

Answer 1

问题在于decoded_noise 不是输入层，因此在定义wext 模型时不能将其作为输入。相反，为您的 wext 模型定义一个新的输入层：

#----------------------w extraction------------------------------------
# Here we define a new input to be used by the wext model
decoded_input = Input((28,28,1)) 
convw1 = Conv2D(64, (3,3), ...)(decoded_input)
convw2 = ...
...
pred_w = ...

wext=Model(inputs=decoded_input, outputs=pred_w)

# Final model: pass the gaussian noise through the wext model
decoded_noise = GaussianNoise(0.5)(decoded)
pred_w = wext(decoded_noise)

final=Model(inputs=[image, wtm], outputs=[decoded, pred_w])