转自https://github.com/ashishpatel26/Tools-to-Design-or-Visualize-Architecture-of-Neural-Network

本期介绍几个可以轻松可视化神经网络的工具，可以用作论文中的画模型图，还可以平日里加深自己对网络的理解。

1  draw_convnet

一个用于画卷积神经网络的Python脚本

• https://github.com/gwding/draw_convnet

2  NNSVG

• http://alexlenail.me/NN-SVG/LeNet.html

3  PlotNeuralNet

• https://github.com/HarisIqbal88/PlotNeuralNet
  

使用latex 来展示神经网络

4  Tensorboard

• https://www.tensorflow.org/tensorboard/graphs

5  Caffe

• https://github.com/BVLC/caffe/blob/master/python/caffe/draw.py
  

使用Caffe/draw.py

6  Matlab

• http://www.mathworks.com/help/nnet/ref/view.html
  

7  Keras.js

• https://transcranial.github.io/keras-js/#/inception-v3
  
  

8  DotNet

• https://github.com/martisak/dotnets

9  Graphviz

• http://www.graphviz.org/

10  ConX

• https://conx.readthedocs.io/en/latest/index.html
  

11  ENNUI 

• https://math.mit.edu/ennui/

12  Neataptic

• https://wagenaartje.github.io/neataptic/