• 使用Keras框架（后端可選tensorflow或者theano），可以畫出卷積神經(jīng)網(wǎng)絡(luò)的結(jié)構(gòu)圖幫助我們理解或確認(rèn)自己創(chuàng)立的模型。
• 問題的關(guān)鍵在于使用from keras.utils.visualize_util import plot中的plot函數(shù)。
  但是直接使用會提示缺少pydot。
  首先安裝sudo pip3 install pydot以及sudo apt-get install graphviz（在Ubuntu上）。
• 但是會提示一個和新版keras的兼容問題。于是我們需要安裝sudo pip3 install pydot-ng來解決這個問題。
• 現(xiàn)在就可以畫出結(jié)構(gòu)圖了：

使用樣例一

from keras.layers import Input, Convolution2D, Flatten, Dense, Activation
from keras.models import Sequential
from keras.optimizers import SGD , Adam
from keras.initializations import normal
from keras.utils.visualize_util import plot

# apply a 3x3 convolution with 64 output filters on a 256x256 image:
model = Sequential()
model.add(Convolution2D(64, 3, 3, border_mode='same', dim_ordering='th',input_shape=(3, 256, 256)))
# now model.output_shape == (None, 64, 256, 256)

# add a 3x3 convolution on top, with 32 output filters:
model.add(Convolution2D(32, 3, 3, border_mode='same', dim_ordering='th'))
# now model.output_shape == (None, 32, 256, 256)
adam = Adam(lr=1e-6)
model.compile(loss='mse',optimizer=adam)
print("We finish building the model")

plot(model, to_file='model1.png', show_shapes=True)

樣例一

使用樣例二

from keras.layers import Input, Convolution2D, MaxPooling2D, Flatten, Dense
from keras.models import Model
from keras.utils.visualize_util import plot

inputs = Input(shape=(229, 229, 3))

x = Convolution2D(32, 3, 3, subsample=(2, 2), border_mode='valid', dim_ordering='tf')(inputs)

x = Flatten()(x)
loss = Dense(32, activation='relu', name='loss')(x)
model = Model(input=inputs, output=loss)
model.compile(optimizer='rmsprop', loss='binary_crossentropy')

# visualize model layout with pydot_ng
plot(model, to_file='model2.png', show_shapes=True)

樣例二

使用樣例三

from keras.layers import Input, Convolution2D, Flatten, Dense, Activation
from keras.models import Sequential
from keras.optimizers import SGD , Adam
from keras.initializations import normal
from keras.utils.visualize_util import plot

print("Now we build the model")
model = Sequential()
img_channels = 4 #output dimenson nothing with channels
img_rows = 80
img_cols = 80
model.add(Convolution2D(32, 8, 8, subsample=(4,4),init=lambda shape, name: normal(shape, scale=0.01, name=name), border_mode='same', dim_ordering='th',input_shape=(img_channels,img_rows,img_cols)))
model.add(Activation('relu'))
model.add(Convolution2D(64, 4, 4, subsample=(2,2),init=lambda shape, name: normal(shape, scale=0.01, name=name), border_mode='same', dim_ordering='th'))
model.add(Activation('relu'))
model.add(Convolution2D(64, 3, 3, subsample=(1,1),init=lambda shape, name: normal(shape, scale=0.01, name=name), border_mode='same', dim_ordering='th'))
model.add(Activation('relu'))
model.add(Flatten())
model.add(Dense(512, init=lambda shape, name: normal(shape, scale=0.01, name=name)))
model.add(Activation('relu'))
model.add(Dense(2,init=lambda shape, name: normal(shape, scale=0.01, name=name)))

adam = Adam(lr=1e-6)
model.compile(loss='mse',optimizer=adam)
print("We finish building the model")

plot(model, to_file='model3.png', show_shapes=True)

model3