tensorflow的可视化工具是tensorboard,但是tensorboard在显示网络结构图的时候,显示特别混乱.
之前看了caffe的可视化网络图,很清晰,最近发现pytorch的网络图可视化工具,对网络图的显示也很清晰.
第一步:安装:
一行命令安装
conda install -c anaconda graphviz python-graphviz
第二步:可视化代码(最好自己单独写一个.py文件)
比如我,写了一个net_view.py
from graphviz import Digraph
from torch.autograd import Variable
import torch
def make_dot(var, params=None):
""" Produces Graphviz representation of PyTorch autograd graph
Blue nodes are the Variables that require grad, orange are Tensors
saved for backward in torch.autograd.Function
Args:
var: output Variable
params: dict of (name, Variable) to add names to node that
require grad (TODO: make optional)
"""
if params is not None:
assert isinstance(params.values()[0], Variable)
param_map = {id(v): k for k, v in params.items()}
node_attr = dict(style='filled',
shape='box',
align='left',
fontsize='12',
ranksep='0.1',
height='0.2')
dot = Digraph(node_attr=node_attr, graph_attr=dict(size="12,12"))
seen = set()
def size_to_str(size):
return '('+(', ').join(['%d' % v for v in size])+')'
def add_nodes(var):
if var not in seen:
if torch.is_tensor(var):
dot.node(str(id(var)), size_to_str(var.size()), fillcolor='orange')
elif hasattr(var, 'variable'):
u = var.variable
name = param_map[id(u)] if params is not None else ''
node_name = '%s\n %s' % (name, size_to_str(u.size()))
dot.node(str(id(var)), node_name, fillcolor='lightblue')
else:
dot.node(str(id(var)), str(type(var).__name__))
seen.add(var)
if hasattr(var, 'next_functions'):
for u in var.next_functions:
if u[0] is not None:
dot.edge(str(id(u[0])), str(id(var)))
add_nodes(u[0])
if hasattr(var, 'saved_tensors'):
for t in var.saved_tensors:
dot.edge(str(id(t)), str(id(var)))
add_nodes(t)
add_nodes(var.grad_fn)
return dot
第三步:主函数调用上面代码,显示网络
import argparse, os
import torch
import random
import torch.backends.cudnn as cudnn
import torch.nn as nn
import torch.optim as optim
from torch.autograd import Variable
import time
from Net import net_view
def net_graph():
model = CNN_Net.Gen_Net()
x = Variable(torch.randn(1, 1, 64, 64))
x1 = Variable(torch.randn(1, 1, 64, 64))
x2 = Variable(torch.randn(1, 1, 64, 64))
x3 = Variable(torch.randn(1, 1, 64, 64))
y = model(x, x1, x2, x3)#我的网络有4个输入,你自己的网络可以按着自己的情况来
g = net_view.make_dot(y)
g.view()
#下面是手动输出参数信息![在这里插入图片描述](https://img-blog.csdn.net/20181009155538749?watermark/2/text/aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0NWX1lPVQ==/font/5a6L5L2T/fontsize/400/fill/I0JBQkFCMA==/dissolve/70)
params = list(model.parameters())
k = 0
for i in params:
l = 1
print("该层的结构:" + str(list(i.size())))
for j in i.size():
l *= j
print("该层参数和:" + str(l))
k = k + l
print("总参数数量和:" + str(k))
if __name__ == "__main__":
net_graph()
参考链接:https://blog.csdn.net/Lucifer_zzq/article/details/80657513
https://github.com/szagoruyko/pytorchviz