這個地方一直是我思考的地方！因為學的代碼太多了，構建的模型各有不同，這里記錄一下！
可以使用以下3種方式構建模型：

1，繼承nn.Module基類構建自定義模型。

2，使用nn.Sequential按層順序構建模型。

3，繼承nn.Module基類構建模型并輔助應用模型容器進行封裝(nn.Sequential,nn.ModuleList,nn.ModuleDict)。

其中 第1種方式最為常見，第2種方式最簡單，第3種方式最為靈活也較為復雜。

推薦使用第1種方式構建模型。

頭文件：

import torch 
from torch import nn

一，繼承nn.Module基類構建自定義模型

以下是繼承nn.Module基類構建自定義模型的一個范例。模型中的用到的層一般在__init__函數中定義，然后在forward方法中定義模型的正向傳播邏輯。

class Net(nn.Module):def __init__(self):super(Net, self).__init__()self.conv1 = nn.Conv2d(in_channels=3,out_channels=32,kernel_size = 3)self.pool1 = nn.MaxPool2d(kernel_size = 2,stride = 2)self.conv2 = nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5)self.pool2 = nn.MaxPool2d(kernel_size = 2,stride = 2)self.dropout = nn.Dropout2d(p = 0.1)self.adaptive_pool = nn.AdaptiveMaxPool2d((1,1))self.flatten = nn.Flatten()self.linear1 = nn.Linear(64,32)self.relu = nn.ReLU()self.linear2 = nn.Linear(32,1)self.sigmoid = nn.Sigmoid()def forward(self,x):x = self.conv1(x)x = self.pool1(x)x = self.conv2(x)x = self.pool2(x)x = self.dropout(x)x = self.adaptive_pool(x)x = self.flatten(x)x = self.linear1(x)x = self.relu(x)x = self.linear2(x)y = self.sigmoid(x)return ynet = Net()
print(net)

二，使用nn.Sequential按層順序構建模型

使用nn.Sequential按層順序構建模型無需定義forward方法。僅僅適合于簡單的模型。

以下是使用nn.Sequential搭建模型的一些等價方法。

1，利用add_module方法

net = nn.Sequential()
net.add_module("conv1",nn.Conv2d(in_channels=3,out_channels=32,kernel_size = 3))
net.add_module("pool1",nn.MaxPool2d(kernel_size = 2,stride = 2))
net.add_module("conv2",nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5))
net.add_module("pool2",nn.MaxPool2d(kernel_size = 2,stride = 2))
net.add_module("dropout",nn.Dropout2d(p = 0.1))
net.add_module("adaptive_pool",nn.AdaptiveMaxPool2d((1,1)))
net.add_module("flatten",nn.Flatten())
net.add_module("linear1",nn.Linear(64,32))
net.add_module("relu",nn.ReLU())
net.add_module("linear2",nn.Linear(32,1))
net.add_module("sigmoid",nn.Sigmoid())print(net)

2，利用變長參數

這種方式構建時不能給每個層指定名稱。

net = nn.Sequential(nn.Conv2d(in_channels=3,out_channels=32,kernel_size = 3),nn.MaxPool2d(kernel_size = 2,stride = 2),nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5),nn.MaxPool2d(kernel_size = 2,stride = 2),nn.Dropout2d(p = 0.1),nn.AdaptiveMaxPool2d((1,1)),nn.Flatten(),nn.Linear(64,32),nn.ReLU(),nn.Linear(32,1),nn.Sigmoid()
)print(net)

3，利用OrderedDict

from collections import OrderedDictnet = nn.Sequential(OrderedDict([("conv1",nn.Conv2d(in_channels=3,out_channels=32,kernel_size = 3)),("pool1",nn.MaxPool2d(kernel_size = 2,stride = 2)),("conv2",nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5)),("pool2",nn.MaxPool2d(kernel_size = 2,stride = 2)),("dropout",nn.Dropout2d(p = 0.1)),("adaptive_pool",nn.AdaptiveMaxPool2d((1,1))),("flatten",nn.Flatten()),("linear1",nn.Linear(64,32)),("relu",nn.ReLU()),("linear2",nn.Linear(32,1)),("sigmoid",nn.Sigmoid())]))
print(net)

三，繼承nn.Module基類構建模型并輔助應用模型容器進行封裝

當模型的結構比較復雜時，我們可以應用模型容器(nn.Sequential,nn.ModuleList,nn.ModuleDict)對模型的部分結構進行封裝。

這樣做會讓模型整體更加有層次感，有時候也能減少代碼量。

注意，在下面的范例中我們每次僅僅使用一種模型容器，但實際上這些模型容器的使用是非常靈活的，可以在一個模型中任意組合任意嵌套使用。

1，nn.Sequential作為模型容器

class Net(nn.Module):def __init__(self):super(Net, self).__init__()self.conv = nn.Sequential(nn.Conv2d(in_channels=3,out_channels=32,kernel_size = 3),nn.MaxPool2d(kernel_size = 2,stride = 2),nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5),nn.MaxPool2d(kernel_size = 2,stride = 2),nn.Dropout2d(p = 0.1),nn.AdaptiveMaxPool2d((1,1)))self.dense = nn.Sequential(nn.Flatten(),nn.Linear(64,32),nn.ReLU(),nn.Linear(32,1),nn.Sigmoid())def forward(self,x):x = self.conv(x)y = self.dense(x)return y net = Net()
print(net)

2，nn.ModuleList作為模型容器

class Net(nn.Module):def __init__(self):super(Net, self).__init__()self.layers = nn.ModuleList([nn.Conv2d(in_channels=3,out_channels=32,kernel_size = 3),nn.MaxPool2d(kernel_size = 2,stride = 2),nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5),nn.MaxPool2d(kernel_size = 2,stride = 2),nn.Dropout2d(p = 0.1),nn.AdaptiveMaxPool2d((1,1)),nn.Flatten(),nn.Linear(64,32),nn.ReLU(),nn.Linear(32,1),nn.Sigmoid()])def forward(self,x):for layer in self.layers:x = layer(x)return x
net = Net()
print(net)

3，nn.ModuleDict作為模型容器

注意下面中的ModuleDict不能用Python中的字典代替。

class Net(nn.Module):def __init__(self):super(Net, self).__init__()self.layers_dict = nn.ModuleDict({"conv1":nn.Conv2d(in_channels=3,out_channels=32,kernel_size = 3),"pool": nn.MaxPool2d(kernel_size = 2,stride = 2),"conv2":nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5),"dropout": nn.Dropout2d(p = 0.1),"adaptive":nn.AdaptiveMaxPool2d((1,1)),"flatten": nn.Flatten(),"linear1": nn.Linear(64,32),"relu":nn.ReLU(),"linear2": nn.Linear(32,1),"sigmoid": nn.Sigmoid()})def forward(self,x):layers = ["conv1","pool","conv2","pool","dropout","adaptive","flatten","linear1","relu","linear2","sigmoid"]for layer in layers:x = self.layers_dict[layer](x)return x
net = Net()
print(net)