Keras中神经网络可视化

1，tensorboard。详见https://github.com/tensorflow/tensorboard/blob/master/README.md。

2，plot_model，对应python3。plot，对应python2。

3，按步骤安装graphviz，pydot，pydot-ng。

4，graphviz的安装详见https://blog.csdn.net/qq_35603331/article/details/81591949，适用于win，msi文件链接https://graphviz.gitlab.io/_pages/Download/Download_windows.html。

5，pydot，pydot-ng对应版本以及安装详见https://blog.csdn.net/lyb3b3b/article/details/74495002。

6，神经网络图例测试详见https://www.jianshu.com/p/56a05b5e4f20。

7，代码和测试结果如下所示。

from keras.layers import Input, Convolution2D, Flatten, Dense, Activation 
from keras.models import Sequential 
from keras.optimizers import SGD , Adam 
from keras.utils import plot_model

# 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)