如何在使用tensorflow进行迁移学习的模型之前添加几层

Question

我正在尝试在 tensorflow 中使用迁移学习。我知道高级范式

base_model=MobileNet(weights='imagenet',include_top=False) #imports the 

mobilenet model and discards the last 1000 neuron layer.

x=base_model.output
x=GlobalAveragePooling2D()(x)
x=Dense(1024,activation='relu')(x) #we add dense layers so that the model can learn more complex functions and classify for better results.
x=Dense(1024,activation='relu')(x) #dense layer 2
x=Dense(512,activation='relu')(x) #dense layer 3
preds=Dense(120,activation='softmax')(x) #final layer with softmax activation

然后通过

编译

model=Model(inputs=base_model.input,outputs=preds)

但是我希望在 base_model.input 之前还有一些其他层。我想为输入的图像和其他一些东西添加对抗性噪声。所以实际上我想知道如何:

base_model=MobileNet(weights='imagenet',include_top=False) #imports the 

mobilenet model and discards the last 1000 neuron layer

x = somerandomelayers(x_in)
base_model.input = x_in
x=base_model.output
x=GlobalAveragePooling2D()(x)
x=Dense(1024,activation='relu')(x) #we add dense layers so that the model can learn more complex functions and classify for better results.
x=Dense(1024,activation='relu')(x) #dense layer 2
x=Dense(512,activation='relu')(x) #dense layer 3
preds=Dense(120,activation='softmax')(x) #final layer with softmax activation
model=Model(inputs=x_in,outputs=preds)

但是行 base_model.input = x_in 显然不是这样做的方法，因为它会抛出 can't set attribute 错误。我如何着手实现所需的行为？

Answer 1

您需要定义输入层。这很简单，只要确保设置正确的形状即可。例如，您可以使用 Keras 中的任何预定义模型。

base_model = keras.applications.any_model(...)
input_layer = keras.layers.Input(shape)
x = keras.layers.Layer(...)(input_layer)
...
x = base_model(x)
...
output = layers.Dense(num_classes, activation)(x)
model = keras.Model(inputs=input_layer, outputs=output)

如何在使用tensorflow进行迁移学习的模型之前添加几层

How to add a few layers before the model in transfer learning with tensorflow

keras

tensorflow

transfer-learning

tf.keras

mobilenet