Pytorch创建模型的多种方法

目录

• 网络结构：
• 导入包

网络结构：

conv --> relu --> pool --> FC -- > relu --> FC

导入包

import torch
import torch.nn.functional as F
from collections import OrderedDict
from torchsummary import summary

Method 1

class Net1(torch.nn.Module):
    def __init__(self):
        super(Net1, self).__init__()
        self.conv1 = torch.nn.Conv2d(3, 32, 3, 1, 1)
        self.dense1 = torch.nn.Linear(32 * 3 * 3, 128)
        self.dense2 = torch.nn.Linear(128, 10)

    def forward(self, x):
        # [2, 3, 6, 6]
        x = F.max_pool2d(F.relu(self.conv1(x)), 2)
        x = x.view(x.size(0), -1)
        x = F.relu(self.dense1(x))
        x = self.dense2(x)
        return x

print("Method 1:")
summary(Net1(), (3, 6, 6))

Method 2

class Net2(torch.nn.Module):
    def __init__(self):
        super(Net2, self).__init__()
        self.conv = torch.nn.Sequential(torch.nn.Conv2d(3, 32, 3, 1, 1),
                                        torch.nn.ReLU(), torch.nn.MaxPool2d(2))
        self.dense = torch.nn.Sequential(torch.nn.Linear(32 * 3 * 3, 128),
                                         torch.nn.ReLU(),
                                         torch.nn.Linear(128, 10))

    def forward(self, x):
        # [2, 3, 6, 6]
        x = self.conv(x)
        x = x.view(x.size(0), -1)
        x = self.dense(x)
        return x

print("Method 2:")
summary(Net2(), (3, 6, 6))

Method 3

class Net3(torch.nn.Module):
    def __init__(self):
        super(Net3, self).__init__()
        self.conv = torch.nn.Sequential()
        self.conv.add_module("conv1", torch.nn.Conv2d(3, 32, 3, 1, 1))
        self.conv.add_module("relu1", torch.nn.ReLU())
        self.conv.add_module("pool1", torch.nn.MaxPool2d(2))
        self.dense = torch.nn.Sequential()
        self.dense.add_module("dense1", torch.nn.Linear(32 * 3 * 3, 128))
        self.dense.add_module("relu2", torch.nn.ReLU())
        self.dense.add_module("dense2", torch.nn.Linear(128, 10))

    def forward(self, x):
        # [2, 3, 6, 6]
        x = self.conv(x)
        x = x.view(x.size(0), -1)
        x = self.dense(x)
        return x

print("Method 3:")
#summary(Net3(), (3, 6, 6))
print(Net3())

这种方法是对第二种方法的改进：通过add_module()添加每一层，并且为每一层增加了一个单独的名字。

Method 4

class Net4(torch.nn.Module):
    def __init__(self):
        super(Net4, self).__init__()
        self.conv = torch.nn.Sequential(
            OrderedDict([("conv1", torch.nn.Conv2d(3, 32, 3, 1, 1)),
                         ("relu1", torch.nn.ReLU()),
                         ("pool", torch.nn.MaxPool2d(2))]))

        self.dense = torch.nn.Sequential(
            OrderedDict([("dense1", torch.nn.Linear(32 * 3 * 3, 128)),
                         ("relu2", torch.nn.ReLU()),
                         ("dense2", torch.nn.Linear(128, 10))]))

    def forward(self, x):
        # [2, 3, 6, 6]
        x = self.conv(x)
        x = x.view(x.size(0), -1)
        x = self.dense(x)
        return x

print("Method 4:")
#summary(Net4(), (3, 6, 6))
print(Net4())

是第三种方法的另外一种写法，通过字典的形式添加每一层，并且设置单独的层名称。

Reference

https://www.cnblogs.com/denny402/p/7593301.html