Pytorch 模型的网络结构可视化
Keras 中 keras.summary() 即可很好的将模型结构可视化，但 Pytorch 暂还没有提供网络模型可视化的工具.
总结两种pytorch网络结构的可视化方法
Pytorch使用Tensorboard可视化网络结构
GitHub地址：点击打开
1.下载可视化代码
git clone https://github.com/lanpa/tensorboard-pytorch.git
2.安装PyTorch 0.4 +torchvision 0.2
3.安装Tensorflow和Tensorboard：
pip install tensorflow
pip install tensorboard==1.7.0
4.安装可视化工具：
pip install tensorboardX
5.运行下面的测试代码demo_LeNet.py :
import torch
import torch.nn as nn
from tensorboardX import SummaryWriter
class LeNet(nn.Module):
def __init__(self):
super(LeNet, self).__init__()
self.conv1 = nn.Sequential( #input_size=(1*28*28)
nn.Conv2d(1, 6, 5, 1, 2),
nn.ReLU(), #(6*28*28)
nn.MaxPool2d(kernel_size=2, stride=2), #output_size=(6*14*14)
)
self.conv2 = nn.Sequential(
nn.Conv2d(6, 16, 5),
nn.ReLU(), #(16*10*10)
nn.MaxPool2d(2, 2) #output_size=(16*5*5)
)
self.fc1 = nn.Sequential(
nn.Linear(16 * 5 * 5, 120),
nn.ReLU()
)
self.fc2 = nn.Sequential(
nn.Linear(120, 84),
nn.ReLU()
)
self.fc3 = nn.Linear(84, 10)
# 定义前向传播过程，输入为x
def forward(self, x):
x = self.conv1(x)
x = self.conv2(x)
# nn.Linear()的输入输出都是维度为一的值，所以要把多维度的tensor展平成一维
x = x.view(x.size()[0], -1)
x = self.fc1(x)
x = self.fc2(x)
x = self.fc3(x)
return x
dummy_input = torch.rand(13, 1, 28, 28) #假设输入13张1*28*28的图片
model = LeNet()
with SummaryWriter(comment='LeNet') as w:
w.add_graph(model, (dummy_input, ))
5.上面的代码运行结束后，会在当前目录生成一个叫run的文件夹，里面存储了可视化所需要的日志信息。用cmd进入到runs文件夹所在的目录中（路劲中不能有中文），然后cmd中输入：
tensorboard --logdir runs
作者：以梦为马_Sun
来源：****
原文：https://blog.****.net/sunqiande88/article/details/80155925?utm_source=copy
使用Github 中的 pytorchviz 可以很不错的画出 Pytorch 模型网络结构.
sudo pip install graphviz
或
sudo pip install git+https://github.com/szagoruyko/pytorchviz
模型可视化函数 - make_dot()
https://github.com/szagoruyko/pytorchviz/blob/master/torchviz/dot.py
import torch
from torch.autograd import Variable
from graphviz import Digraph
def make_dot(var, params=None):
"""
画出 PyTorch 自动梯度图 autograd graph 的 Graphviz 表示.
蓝色节点表示有梯度计算的变量Variables;
橙色节点表示用于 torch.autograd.Function 中的 backward 的张量 Tensors.
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 all(isinstance(p, Variable) for p in params.values())
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]) + ')'
output_nodes = (var.grad_fn,) if not isinstance(var, tuple) else tuple(v.grad_fn for v in var)
def add_nodes(var):
if var not in seen:
if torch.is_tensor(var):
# note: this used to show .saved_tensors in pytorch0.2, but stopped
# working as it was moved to ATen and Variable-Tensor merged
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')
elif var in output_nodes:
dot.node(str(id(var)), str(type(var).__name__), fillcolor='darkolivegreen1')
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)
# 多输出场景 multiple outputs
if isinstance(var, tuple):
for v in var:
add_nodes(v.grad_fn)
else:
add_nodes(var.grad_fn)
resize_graph(dot)
return dot
Demo - MLP
https://github.com/szagoruyko/pytorchviz/blob/master/examples.ipynb
python2.7
import torch
from torch import nn
from torchviz import make_dot
model = nn.Sequential()
model.add_module('W0', nn.Linear(8, 16))
model.add_module('tanh', nn.Tanh())
model.add_module('W1', nn.Linear(16, 1))
x = torch.randn(1,8)
vis_graph = make_dot(model(x), params=dict(model.named_parameters()))
vise_graph.view()
Demo - AlexNet
import torch
from torch import nn
from torchviz import make_dot
from torchvision.models import AlexNet
model = AlexNet()
x = torch.randn(1, 3, 227, 227).requires_grad_(True)
y = model(x)
vis_graph = make_dot(y, params=dict(list(model.named_parameters()) + [('x', x)]))
vise_graph.view()
模型参数打印
import torch
from torch import nn
from torchviz import make_dot
from torchvision.models import AlexNet
model = AlexNet()
x = torch.randn(1, 3, 227, 227).requires_grad_(True)
y = model(x)
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))
输出如下：
该层的结构：[64, 3, 11, 11] 该层参数和：23232 该层的结构：[64] 该层参数和：64 该层的结构：[192, 64, 5, 5] 该层参数和：307200 该层的结构：[192] 该层参数和：192 该层的结构：[384, 192, 3, 3] 该层参数和：663552 该层的结构：[384] 该层参数和：384 该层的结构：[256, 384, 3, 3] 该层参数和：884736 该层的结构：[256] 该层参数和：256 该层的结构：[256, 256, 3, 3] 该层参数和：589824 该层的结构：[256] 该层参数和：256 该层的结构：[4096, 9216] 该层参数和：37748736 该层的结构：[4096] 该层参数和：4096 该层的结构：[4096, 4096] 该层参数和：16777216 该层的结构：[4096] 该层参数和：4096 该层的结构：[1000, 4096] 该层参数和：4096000 该层的结构：[1000] 该层参数和：1000 总参数数量和：1000