У меня есть автокодер с двумя входами, image (28x28) и wtm (28x28).Я добавляю wtm с выводом части кодера и отправляю его части декодера.мой основной вес был 4x4, но, поскольку я не знаю, как я могу добавить его с тензором размером 28x28, я должен поместить это случайное изображение 4x4 в верхний левый угол изображения с нулями 28x28.наконец, в выходных данных моей сети мне нравится сравнивать предсказанный весовой коэффициент с размером (4х4) с верхней левой частью весового коэффициента, а не с целым в функции потерь.Является ли это возможным?(Я использую wtm [:, 0: 4,0: 4 ,:] в функции потерь?), Пожалуйста, помогите мне с этим вопросом.если у вас есть решение, которое не нужно расширять wtm на первом этапе, пожалуйста, скажите мне.
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)