我有一个带有两个输入的自动编码器，图像（28x28）和wtm（28x28）。我将wtm与编码器部分的输出相加，并将其发送到解码器部分。我的主要wtm是4x4，但是由于我不知道如何使用大小为28x28的张量添加它，因此我必须将此4x4随机图像放在28x28零图像的左上角。最后，在网络的输出中，我想将大小为（4x4）的预测wtm与wtm的左上部分进行比较，而不是将其整个损失函数进行比较。可能吗？ （我在损失函数中使用wtm [：，0：4,0：4 ,:]？）请帮助我解决这个问题。如果您有任何解决方案不需要在第一阶段扩展wtm，请告诉我。
from keras.layers import Input, Concatenate, GaussianNoise,Dropout,BatchNormalization,MaxPool2D,AveragePooling2D
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;
#-----------------building w train---------------------------------------------
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')(image)
conv2 = Conv2D(64, (5, 5), activation='relu', padding='same', name='convl2e')(conv1)
conv3 = Conv2D(64, (5, 5), 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)
BN=BatchNormalization()(conv3)
#DrO1=Dropout(0.25,name='Dro1')(BN)
encoded = Conv2D(1, (5, 5), activation='relu', padding='same',name='encoded_I')(BN)
#-----------------------adding w---------------------------------------
#add_const = Kr.layers.Lambda(lambda x: x + wtm)
#encoded_merged = add_const(encoded)
add_const = Kr.layers.Lambda(lambda x: x[0] + x[1])
encoded_merged = add_const([encoded,wtm])
#-----------------------decoder------------------------------------------------
#------------------------------------------------------------------------------
#deconv_input=Input((28,28,1),name='inputTodeconv')
#encoded_merged = Input((28, 28, 2))
deconv1 = Conv2D(64, (5, 5), activation='elu', padding='same', name='convl1d')(encoded_merged)
deconv2 = Conv2D(64, (5, 5), activation='elu', padding='same', name='convl2d')(deconv1)
deconv3 = Conv2D(64, (5, 5), activation='elu',padding='same', name='convl3d')(deconv2)
deconv4 = Conv2D(64, (5, 5), activation='elu',padding='same', name='convl4d')(deconv3)
BNd=BatchNormalization()(deconv3)
#DrO2=Dropout(0.25,name='DrO2')(BNd)
decoded = Conv2D(1, (5, 5), activation='sigmoid', padding='same', name='decoder_output')(BNd)
#model=Model(inputs=image,outputs=decoded)
model=Model(inputs=[image,wtm],outputs=decoded)
decoded_noise = GaussianNoise(0.5)(decoded)
#----------------------w extraction------------------------------------
convw1 = Conv2D(64, (3,3), activation='relu', name='conl1w')(decoded_noise)
convw2 = Conv2D(64, (3, 3), activation='relu', name='convl2w')(convw1)
Avw1=AveragePooling2D(pool_size=(2,2))
convw3 = Conv2D(64, (3, 3), activation='relu', padding='same', name='conl3w')(convw2)
convw4 = Conv2D(64, (3, 3), activation='relu', padding='same', name='conl4w')(convw3)
Avw2=AveragePooling2D(pool_size=(2,2))
convw5 = Conv2D(64, (3, 3), activation='relu', name='conl5w')(convw4)
convw6 = Conv2D(64, (3, 3), activation='relu', padding='same', name='conl6w')(convw5)
BNed=BatchNormalization()(convw6)
#DrO3=Dropout(0.25, name='DrO3')(BNed)
pred_w = Conv2D(1, (1, 1), activation='sigmoid', padding='same', name='reconstructed_W')(BNed)
# reconsider activation (is W positive?)
# should be filter=1 to match W
watermark_extraction=Model(inputs=[image,wtm[:,0:4,0:4,:]],outputs=[decoded,pred_w])
watermark_extraction.summary()
#----------------------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------------------------------
opt=SGD(momentum=0.99)
watermark_extraction.compile(optimizer=opt, loss={'decoder_output':'mse','reconstructed_W':'binary_crossentropy'}, loss_weights={'decoder_output': 0.75, 'reconstructed_W': 1.0},metrics=['mae'])
es = EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=20)
rlrp = ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=20, min_delta=1E-4, verbose=1)
mc = ModelCheckpoint('best_model_5x5F_dp_gn.h5', monitor='val_loss', mode='min', verbose=1, save_best_only=True)
history=watermark_extraction.fit([x_train,w_expand], [x_train,w_expand],
epochs=200,
batch_size=32,
validation_data=([x_validation,wv_expand], [x_validation,wv_expand]),
callbacks=[TensorBoard(log_dir='E:/concatnatenetwork', histogram_freq=0, write_graph=False),rlrp,es,mc])
watermark_extraction.summary()
WEIGHTS_FNAME = 'v1_sgd_model_5x5F_cocat_dp_gn.hdf'
watermark_extraction.save_weights(WEIGHTS_FNAME, overwrite=True)