Rewriting keras example

convnet.py

from keras.models import Sequential
from keras.layers import Convolution2D, ZeroPadding2D, MaxPooling2D

img_width, img_height = 128, 128

# this will contain our generated images
input_img = K.placeholder((1, 3, img_width, img_height))

# build the VGG16 network with our input_img as input
first_layer = ZeroPadding2D((1, 1), input_shape=(3, img_width, img_height))
first_layer.input = input_img

model = Sequential()
model.add(first_layer)
model.add(Convolution2D(64, 3, 3, activation='relu', name='conv1_1'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(64, 3, 3, activation='relu', name='conv1_2'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))

model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(128, 3, 3, activation='relu', name='conv2_1'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(128, 3, 3, activation='relu', name='conv2_2'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))

model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(256, 3, 3, activation='relu', name='conv3_1'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(256, 3, 3, activation='relu', name='conv3_2'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(256, 3, 3, activation='relu', name='conv3_3'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))

model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv4_1'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv4_2'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv4_3'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))

model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv5_1'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv5_2'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv5_3'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))

# get the symbolic outputs of each "key" layer (we gave them unique names).
layer_dict = dict([(layer.name, layer) for layer in model.layers])

rewrite.py

from keras.models import Sequential
from keras.layers import Convolution2D, ZeroPadding2D, MaxPooling2D

img_width, img_height = 128, 128
input_img = K.placeholder((1, 3, img_width, img_height))

# build the VGG16 network with our input_img as input
first_layer = ZeroPadding2D((1, 1), input_shape=(3, img_width, img_height))
first_layer.input = input_img
Z = ZeroPadding2D((1, 1)))
MP = MaxPooling2D((2, 2), strides=(2, 2)))

# The fundamental information here is really contained in the following specification. 
# Create groups for each element of list, where element is net size: [64,128,256,512,512]
# Each group will have some number of pairs of convolutional and zero padding elements. For the groups above: [2,2,3,3,3]
# The first pair of the first group actually isn't a pair. Instead of starting with the usual Z, it has a slightly special Z. 
# each Group ends with a max pooling element. 

# get the symbolic outputs of each "key" layer (we gave them unique names).
layer_dict = dict([(layer.name, layer) for layer in model.layers])


# #C1 = Convolution2D(64, 3, 3, activation='relu')
# N = [64,128,256,512,512]

# model = Sequential()
# model.add(first_layer)
# C1, Z, C1, MP
# Z, C2, Z, C2, MP
# Z, C3, Z, C3, Z, C3, MP
# Z, C4, Z, C4, Z, C4, MP
# Z, C5, Z, C5, Z, C5, MP