I am trying to use transfer learning in tensorflow. I know the high level paradigm
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
and then one compiles it by
model=Model(inputs=base_model.input,outputs=preds)
However i want the there to be a few other layers before the base_model.input. I want to add adversarial noise to the images that come in and a few other things. So effectively i want to know how to :
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)
but the line base_model.input = x_in is apparently not the way to do it as it throws can't set attribute error. How do i go about achieving the desired behavior?
You need to define input layer. It's rather straightforward, just be sure to set right shapes. For example, you can use any predefined model from Keras.
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)