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/