12个神经网络可视化工具，很酷！

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/