Pytorch网络结构可视化
须知少日拿云志，曾许人间第一流
安装
可以通过以下的命令进行安装
conda install pytorch-nightly -c pytorch
conda install graphviz
conda install torchvision
conda install tensorwatch本教程基于以下的版本：
torchvision.__version__ '0.2.1'
torch.__version__ '1.2.0.dev20190610'
sys.version '3.6.8 |Anaconda custom (64-bit)| (default, Dec 30 2018, 01:22:34) \n[GCC 7.3.0]'载入库
import sys
import torch
import tensorwatch as tw
import torchvision.models网络结构可视化
alexnet_model = torchvision.models.alexnet()
tw.draw_model(alexnet_model, [1, 3, 224, 224])
载入alexnet，draw_model函数需要传入三个参数，第一个为model，第二个参数为input_shape，第三个参数为orientation，可以选择'LR'或者'TB'，分别代表左右布局与上下布局。
在notebook中，执行完上面的代码会显示如下的图，将网络的结构及各个层的name和shape进行了可视化。
统计网络参数
可以通过model_stats方法统计各层的参数情况。
tw.model_stats(alexnet_model, [1, 3, 224, 224])
[MAdd]: Dropout is not supported!
[Flops]: Dropout is not supported!
[Memory]: Dropout is not supported!
[MAdd]: Dropout is not supported!
[Flops]: Dropout is not supported!
[Memory]: Dropout is not supported!
[MAdd]: Dropout is not supported!
[Flops]: Dropout is not supported!
[Memory]: Dropout is not supported!
[MAdd]: Dropout is not supported!
[Flops]: Dropout is not supported!
[Memory]: Dropout is not supported!
[MAdd]: Dropout is not supported!
[Flops]: Dropout is not supported!
[Memory]: Dropout is not supported!
[MAdd]: Dropout is not supported!
[Flops]: Dropout is not supported!
[Memory]: Dropout is not supported!
发布于 2019-06-10 20:36
