我正在尝试在Keras中实施ADDA。这是我的代码:
class ADDA_Images(object):
def __init__(self,modelInput):
self.img_rows = 28
self.img_cols = 28
self.channels = 3
self.img_shape = (self.img_rows, self.img_cols, self.channels)
optimizer = opt.Adam(0.001)
self.source_generator = self.build_generator(modelInput)
self.target_generator = self.build_generator(modelInput)
outputFeatureExtraction = layers.Input(shape = self.target_generator.output_shape[1:])
self.source_classificator = self.build_classifier(outputFeatureExtraction)
self.discriminator_model = self.build_discriminator(outputFeatureExtraction)
self.discriminator_model.compile(optimizer, loss='binary_crossentropy', metrics=['acc'])
self.discriminator_model.name='disk'
input = layers.Input(shape=self.img_shape)
fe_rep = self.source_generator(input)
cl = self.source_classificator(fe_rep)
self.source_model = Model(input,cl)
self.source_model.compile(optimizer, loss='categorical_crossentropy', metrics=['acc'])
input = layers.Input(shape=self.img_shape)
fe_rep = self.target_generator(input)
cl = self.source_classificator(fe_rep)
self.target_model = Model(input, cl)
self.target_model.compile(optimizer, loss='categorical_crossentropy', metrics=['acc'])
self.combined_model = Sequential()
self.combined_model.add(self.target_generator)
self.combined_model.add(self.discriminator_model)
self.combined_model.get_layer('disk').trainable = False
self.combined_model.compile(optimizer, loss='binary_crossentropy', metrics=['acc'])
print('Source model')
self.source_model.summary()
print('Target model')
self.target_model.summary()
print('Discriminator')
self.discriminator_model.summary()
print('Combined model')
self.combined_model.summary()
def build_generator(self,modelInput):
gen = layers.Conv2D(filters=20, kernel_size=5, padding='valid')(modelInput)
gen = layers.MaxPooling2D(pool_size=2, strides=2)(gen)
gen = layers.Conv2D(filters=50, kernel_size=5, padding='valid')(gen)
gen = layers.MaxPooling2D(pool_size=2, strides=2)(gen)
gen = layers.Flatten()(gen)
model = Model(modelInput,gen)
print('Generator summary')
model.summary()
return model
def build_classifier(self,modelInput):
cl = layers.Dense(3072, activation='relu')(modelInput)
cl = layers.Dense(2048, activation='relu')(cl)
cl = layers.Dense(10, activation='softmax')(cl)
model = Model(modelInput,cl)
print('Classificatior summary')
model.summary()
return model
def build_discriminator(self,modelInput):
disc = layers.Dense(500, activation='relu')(modelInput)
disc = layers.Dense(500, activation='relu')(disc)
disc = layers.Dense(2, activation='softmax')(disc)
model = Model(modelInput,disc)
print('Discriminator summary')
model.summary()
return model
但是,似乎target_generator没有连接到目标模型。我从预训练源模型加载目标模型,然后以ADDA方式训练鉴别器和组合模型。但是,目标模型没有改变。它始终与源模型具有相同的预测(accs和loss)。
以下是模型摘要:
Source model
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_2 (InputLayer) (None, 28, 28, 3) 0
_________________________________________________________________
model_1 (Model) (None, 800) 26570
_________________________________________________________________
model_3 (Model) (None, 10) 8774666
=================================================================
Total params: 8,801,236
Trainable params: 8,801,236
Non-trainable params: 0
_________________________________________________________________
Target model
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_3 (InputLayer) (None, 28, 28, 3) 0
_________________________________________________________________
model_2 (Model) (None, 800) 26570
_________________________________________________________________
model_3 (Model) (None, 10) 8774666
=================================================================
Total params: 8,801,236
Trainable params: 8,801,236
Non-trainable params: 0
_________________________________________________________________
Discriminator
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 800) 0
_________________________________________________________________
dense_4 (Dense) (None, 500) 400500
_________________________________________________________________
dense_5 (Dense) (None, 500) 250500
_________________________________________________________________
dense_6 (Dense) (None, 2) 1002
=================================================================
Total params: 1,304,004
Trainable params: 652,002
Non-trainable params: 652,002
_________________________________________________________________
Combined model
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
model_2 (Model) (None, 800) 26570
_________________________________________________________________
disk (Model) (None, 2) 652002
=================================================================
Total params: 678,572
Trainable params: 26,570
Non-trainable params: 652,002
我验证了target_model的第二层(按规格应该是target_generator)的输出,它与target_generator的输出(在同一输入上)不同。因此,似乎这两个模型没有像摘要中所报告的那样连接。
有人可以帮我弄清楚出了什么问题吗?
我使用的是Keras 2,Tensorflow后端。
非常感谢!
答案 0 :(得分:1)
问题在于训练部分 - 我加载到目标模型预训练源模型(load_model)并且因为它改变了对生成器模型的引用而产生了问题。我应该使用load_weights
而不是load_model因此,加载预先训练的模型是有效的,但不会引用参考文献:
source_model = load_model(modelName)
target_model.set_weights(source_model.get_weights())
答案 1 :(得分:0)
@JecaJeca您是否愿意共享其余代码?