Keras画出网络（拓扑）结构

 在linux环境下：使用sudo apt-get install graphviz即可;

谈一谈windows的用法：

Keras中显示网络拓扑结构的包在utils中的plot_model，

from keras.utils import plot_model
# visualize model layout with pydot_ng
plot_model(model, to_file='./model2.png', show_shapes=True)

但是需要依赖包： 

pip install pydot-ng

pip install graphviz

pip install pydot

 然后安装graphviz的客户端：

安装时需要将路径添加到系统环境变量PATH中。

因为你添加到系统环境变量中去了，所以大概率你需要重启。这个重启不一定是系统，还有可能是Jupyter环境。你先重启软件，不行，再重启一下系统。如果是Pycharm你可以像我一样在代码中添加一句：

import os

os.environ["PATH"] += os.pathsep + 'C:/Program Files/Graphviz/bin/'

from keras.layers import Input, Dense, Lambda, Reshape
from keras.models import Model
from keras import backend as K


# defining the key parameters
batch_size = 100
original_dim = 784
latent_dim = 2
intermediate_dim = 256
epsilon_std = 1.0


def sampling(args: tuple):
    # we grab the variables from the tuple
    z_mean, z_log_var = args
    epsilon = K.random_normal(shape=(K.shape(z_mean)[0], latent_dim), mean=0.,
                              stddev=epsilon_std)
    return z_mean + K.exp(z_log_var / 2) * epsilon


# input to our encoder
x = Input(shape=(original_dim,), name="input")
# intermediate layer
h = Dense(intermediate_dim, activation='relu', name="encoding")(x)
# defining the mean of the latent space
z_mean = Dense(latent_dim, name="mean")(h)
# defining the log variance of the latent space
z_log_var = Dense(latent_dim, name="log-variance")(h)
# note that "output_shape" isn't necessary with the TensorFlow backend
z = Lambda(sampling, output_shape=(latent_dim,))([z_mean, z_log_var])
# defining the encoder as a keras model
encoder = Model(x, [z_mean, z_log_var, z], name="encoder")
# print out summary of what we just did
encoder.summary()

# visualize model layout with pydot_ng
from keras.utils import plot_model
import os

os.environ["PATH"] += os.pathsep + 'C:/Program Files/Graphviz/bin/'
plot_model(encoder, to_file='./model2.png', show_shapes=True)