vgg-96-define-model.py

model = Sequential()
model.add(Conv2D(64, kernel_size=(3, 3), input_shape=(96, 96, 3), activation='relu', padding='same'))
model.add(Conv2D(64, kernel_size=(3, 3), input_shape=(96, 96, 3), activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(2, 2)))

# load the pretrained model
prior = load_model('resnet48_128/model-48.h5')

# add all but the first two layers of VGG16 to the new model
# strip the input layer out, this is now 96x96
# also strip out the first convolutional layer, this took the 48x48 input and convolved it but
# this is now the job of the three new layers.
for layer in prior.layers[0].layers[2:]:
    model.add(layer)

# re-add the feedforward layers on top
for layer in prior.layers[1:]:
    model.add(layer)

# the pretrained CNN layers are already marked non-trainable
# mark off the top layers as well
for layer in prior.layers[-4:]:
    layer.trainable = False
    
# compile the model
model.compile(
    optimizer=RMSprop(),
    loss='categorical_crossentropy',
    metrics=['accuracy']
)

for layer in prior.layers[0].layers[2:]:
    model.add(layer)

Can you please explain this piece of code