參考：

https://blog.csdn.net/qq_36427732/article/details/79110736

https://www.cnblogs.com/timxgb/p/9490219.html

1、pydot和pydot_ng安裝

pip install pydot

pip install pydot_ng

2、graphviz安裝

（1）安裝homebrew

homebrew官方網站：https://brew.sh/index_zh-cn

終端輸入如下命令（關掉加速器）：

/usr/bin/ruby -e "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)"
 

（2）安裝graphviz

brew install graphviz

3、模型視覺化

from SSRNET_model import SSR_net
from keras.utils.vis_utils import plot_model

img_size = 64
stage_num = [3,3,3]
lambda_local = 1
lambda_d = 1
weight_file = 'ssrnet_3_3_3_64_morph2_age.h5'
all_file = 'ssrnet_3_3_3_64_morph2_age_all.h5'
model = SSR_net(img_size,stage_num, lambda_local, lambda_d)()
model.load_weights(weight_file)
model.save(all_file)

plot_model(model, to_file='model_ssrnet_all.jpg', show_shapes=True)