我有一个自动编码器,我使用不同的解决方案检查了模型的准确性,例如更改转换层的数量并增加它们,添加或删除批量归一化,更改激活函数,但所有这些解决方案的准确性都是相似的,并且不一样有任何奇怪的改进。我很困惑,因为我认为这些不同解决方案的准确度应该不同,但它是 0.8156。你能帮我看看有什么问题吗?我还用 10000 个 epoch 对其进行训练,但 50 个 epoch 的输出是相同的!我的代码是错误的还是不能变得更好?!准确度图 https://i.stack.imgur.com/KBnrp.png
我也不确定学习率衰减是否有效?!
我也把我的代码放在这里:
from keras.layers import Input, Concatenate, GaussianNoise,Dropout,BatchNormalization
from keras.layers import Conv2D
from keras.models import Model
from keras.datasets import mnist,cifar10
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.callbacks import ReduceLROnPlateau
from keras.callbacks import EarlyStopping
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;
image = Input((28, 28, 1))
conv1 = Conv2D(16, (3, 3), activation='elu', padding='same', name='convl1e')(image)
conv2 = Conv2D(32, (3, 3), activation='elu', padding='same', name='convl2e')(conv1)
conv3 = Conv2D(16, (3, 3), activation='elu', 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')(conv3)
DrO1=Dropout(0.25,name='Dro1')(BN)
encoded = Conv2D(1, (3, 3), activation='elu', padding='same',name='encoded_I')(DrO1)
#-----------------------decoder------------------------------------------------
#------------------------------------------------------------------------------
deconv1 = Conv2D(16, (3, 3), activation='elu', padding='same', name='convl1d')(encoded)
deconv2 = Conv2D(32, (3, 3), activation='elu', padding='same', name='convl2d')(deconv1)
deconv3 = Conv2D(16, (3, 3), activation='elu',padding='same', name='convl3d')(deconv2)
BNd=BatchNormalization()(deconv3)
DrO2=Dropout(0.25,name='DrO2')(BNd)
#DrO2=Dropout(0.5,name='DrO2')(deconv3)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same', name='decoder_output')(DrO2)
#model=Model(inputs=[image,wtm],outputs=decoded)
#--------------------------------adding noise----------------------------------
#decoded_noise = GaussianNoise(0.5)(decoded)
watermark_extraction=Model(inputs=image,outputs=decoded)
watermark_extraction.summary()
#----------------------training the model--------------------------------------
#------------------------------------------------------------------------------
#----------------------Data preparation----------------------------------------
(x_train, _), (x_test, _) = mnist.load_data()
x_validation=x_train[1:10000,:,:]
x_train=x_train[10001:60000,:,:]
#(x_train, _), (x_test, _) = cifar10.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?
learning_rate = 0.1
decay_rate = learning_rate / 50
opt = optimizers.SGD(lr=learning_rate, momentum=0.9, decay=decay_rate, nesterov=False)
watermark_extraction.compile(optimizer=opt, loss=['mse'], metrics=['accuracy'])
es = EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=20)
#rlrp = ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=5, min_delta=1E-7, verbose=1)
history=watermark_extraction.fit(x_train, x_train,
epochs=50,
batch_size=32,
validation_data=(x_validation, x_validation),
callbacks=[TensorBoard(log_dir='E:/output of tensorboard', histogram_freq=0, write_graph=False),es])
watermark_extraction.summary()
#--------------------visuallize the output layers------------------------------
#_, train_acc = watermark_extraction.evaluate(x_train, x_train)
#_, test_acc = watermark_extraction.evaluate([x_test[5000:5001],wt_expand], [x_test[5000:5001],wt_expand])
#print('Train: %.3f, Test: %.3f' % (train_acc, test_acc))
## plot loss learning curves
pyplot.subplot(211)
pyplot.title('MSE Loss', pad=-40)
pyplot.plot(history.history['loss'], label='train')
pyplot.plot(history.history['val_loss'], label='validation')
pyplot.legend()
pyplot.subplot(212)
pyplot.title('Accuracy', pad=-40)
pyplot.plot(history.history['acc'], label='train')
pyplot.plot(history.history['val_acc'], label='test')
pyplot.legend()
pyplot.show