【深度学习】超级赞!N个神经网络可视化利器
共 10593字,需浏览 22分钟
·
2021-09-07 15:21
分享展示神经网络的N个利器。
1、PlotNeuralNet
使用Latex绘制神经网络。传送门:https://github.com/HarisIqbal88/PlotNeuralNet
overleaf上Latex代码:https://www.overleaf.com/read/kkqntfxnvbsk
overleaf上Latex代码:https://www.overleaf.com/read/wsxpmkqvjnbs
overleaf上Latex代码:https://www.overleaf.com/read/jxhnkcnwhfxp
2、Matlab
https://www.mathworks.com/help/deeplearning/ref/view.html;jsessionid=bd77484ba149c98d4d410abed983
[x,t] = iris_dataset;
net = patternnet;
net = configure(net,x,t);
view(net)
3、NN-SVG
一个在线工具,点点就阔以了:http://alexlenail.me/NN-SVG/LeNet.html
4、graphcore
回到神经网络最初的地方,像生物细胞神经元neurons一样展示神经网络。https://www.graphcore.ai/posts/what-does-machine-learning-look-like
5、graphviz
http://www.graphviz.org/
之前介绍过一个类似绘制网络关系的工具👉盘一盘社交网络分析常用networks
6、Keras
深度学习框架Keras下的一个小模块,
https://keras.io/api/utils/model_plotting_utils/
7、neataptic
https://github.com/wagenaartje/neataptic
8、Quiver
https://github.com/keplr-io/quiver
9、Keras.js
在线工具
https://transcranial.github.io/keras-js/#/inception-v3
10、Netscope CNN Analyzer
http://dgschwend.github.io/netscope/quickstart.html
11、keras-sequential-ascii
https://github.com/stared/keras-sequential-ascii/
VGG 16 Architecture
OPERATION DATA DIMENSIONS WEIGHTS(N) WEIGHTS(%)
Input ##### 3 224 224
InputLayer | ------------------- 0 0.0%
##### 3 224 224
Convolution2D \|/ ------------------- 1792 0.0%
relu ##### 64 224 224
Convolution2D \|/ ------------------- 36928 0.0%
relu ##### 64 224 224
MaxPooling2D Y max ------------------- 0 0.0%
##### 64 112 112
Convolution2D \|/ ------------------- 73856 0.1%
relu ##### 128 112 112
Convolution2D \|/ ------------------- 147584 0.1%
relu ##### 128 112 112
MaxPooling2D Y max ------------------- 0 0.0%
##### 128 56 56
Convolution2D \|/ ------------------- 295168 0.2%
relu ##### 256 56 56
Convolution2D \|/ ------------------- 590080 0.4%
relu ##### 256 56 56
Convolution2D \|/ ------------------- 590080 0.4%
relu ##### 256 56 56
MaxPooling2D Y max ------------------- 0 0.0%
##### 256 28 28
Convolution2D \|/ ------------------- 1180160 0.9%
relu ##### 512 28 28
Convolution2D \|/ ------------------- 2359808 1.7%
relu ##### 512 28 28
Convolution2D \|/ ------------------- 2359808 1.7%
relu ##### 512 28 28
MaxPooling2D Y max ------------------- 0 0.0%
##### 512 14 14
Convolution2D \|/ ------------------- 2359808 1.7%
relu ##### 512 14 14
Convolution2D \|/ ------------------- 2359808 1.7%
relu ##### 512 14 14
Convolution2D \|/ ------------------- 2359808 1.7%
relu ##### 512 14 14
MaxPooling2D Y max ------------------- 0 0.0%
##### 512 7 7
Flatten ||||| ------------------- 0 0.0%
##### 25088
Dense XXXXX ------------------- 102764544 74.3%
relu ##### 4096
Dense XXXXX ------------------- 16781312 12.1%
relu ##### 4096
Dense XXXXX ------------------- 4097000 3.0%
softmax ##### 1000
12、TensorBoard
一个评估深度学习框架TensorFlow模型的强力工具。
https://www.tensorflow.org/tensorboard/graphs
13、Caffe
同样是深度学习框架Caffe下的一个小工具,
https://github.com/BVLC/caffe/blob/master/python/caffe/draw.py
14、TensorSpace
3D模式展示神经网络,
https://tensorspace.org/
-END-
往期精彩回顾 本站qq群851320808,加入微信群请扫码: