Keras 中 keras.summary() 即可很好的將模型結構視覺化，但 Pytorch 暫還沒有提供網路模型視覺化的工具.

總結兩種pytorch網路結構的視覺化方法
Pytorch使用Tensorboard視覺化網路結構
GitHub地址：點選開啟
1.下載視覺化程式碼

git clone https://github.com/lanpa/tensorboard-pytorch.git

2.安裝PyTorch 0.4 +torchvision 0.2
3.安裝Tensorflow和Tensorboard：

pip install tensorflow
pip install tensorboard==1.7.0
 

4.安裝視覺化工具：

pip install  tensorboardX

5.執行下面的測試程式碼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)

    # 定義前向傳播過程，輸入為x
    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        # nn.Linear()的輸入輸出都是維度為一的值，所以要把多維度的tensor展平成一維
        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) #假設輸入13張1*28*28的圖片
model = LeNet()
with SummaryWriter(comment='LeNet') as w:
    w.add_graph(model, (dummy_input, ))
 

5.上面的程式碼執行結束後，會在當前目錄生成一個叫run的資料夾，裡面儲存了視覺化所需要的日誌資訊。用cmd進入到runs資料夾所在的目錄中（路勁中不能有中文），然後cmd中輸入：

tensorboard --logdir runs

作者：以夢為馬_Sun
來源：CSDN
原文：https://blog.csdn.net/sunqiande88/article/details/80155925?utm_source=copy
使用Github 中的 pytorchviz 可以很不錯的畫出 Pytorch 模型網路結構.

sudo pip install graphviz
或
sudo pip install git+https://github.com/szagoruyko/pytorchviz
 

模型視覺化函式 - 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):
    """
    畫出 PyTorch 自動梯度圖 autograd graph 的 Graphviz 表示.
    藍色節點表示有梯度計算的變數Variables;
    橙色節點表示用於 torch.autograd.Function 中的 backward 的張量 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)

    # 多輸出場景 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()

模型引數列印

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("該層的結構：" + str(list(i.size())))
        for j in i.size():
                l *= j
        print("該層引數和：" + str(l))
        k = k + l
print("總引數數量和：" + str(k))

輸出如下：

該層的結構：[64, 3, 11, 11]
該層引數和：23232
該層的結構：[64]
該層引數和：64
該層的結構：[192, 64, 5, 5]
該層引數和：307200
該層的結構：[192]
該層引數和：192
該層的結構：[384, 192, 3, 3]
該層引數和：663552
該層的結構：[384]
該層引數和：384
該層的結構：[256, 384, 3, 3]
該層引數和：884736
該層的結構：[256]
該層引數和：256
該層的結構：[256, 256, 3, 3]
該層引數和：589824
該層的結構：[256]
該層引數和：256
該層的結構：[4096, 9216]
該層引數和：37748736
該層的結構：[4096]
該層引數和：4096
該層的結構：[4096, 4096]
該層引數和：16777216
該層的結構：[4096]
該層引數和：4096
該層的結構：[1000, 4096]
該層引數和：4096000
該層的結構：[1000]
該層引數和：1000
總引數數量和：1000

原文地址:https://www.aiuai.cn/aifarm467.html