深度学习从入门到精通——GoogLeNetV1分类算法_googelenet算法(2)

本文链接：https://blog.csdn.net/2401_84926844/article/details/138800722

网上学习资料一大堆，但如果学到的知识不成体系，遇到问题时只是浅尝辄止，不再深入研究，那么很难做到真正的技术提升。

一个人可以走的很快，但一群人才能走的更远！不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人，都欢迎加入我们的的圈子（技术交流、学习资源、职场吐槽、大厂内推、面试辅导），让我们一起学习成长！

def forward(self, x):
    branch1 = self.branch1x1(x)
    branch2 = self.branch3x3(x)
    branch3 = self.branch5x5(x)
    branch4 = self.pool(x)

    outputs = [branch1, branch2, branch3, branch4]
    return torch.cat(outputs, 1)


#### 采用了1\*1卷积


* 1*1 卷积在像素上，由于尺度大小是1*1，所以在像素层面计算基本不会变化，但是根据卷积的原理，1*1卷积之后，会进行通道上的混洗，因此1*1卷积额外提供了特征升维的功能。
* 通过控制1\*1卷积核的个数，可以合理的控制输出的大小，还提供了升维能力


#### 池化层


利用平均池化化来代替全连接：


* 可以直接输入不同形状的图片
* 计算量大大减少  
 完整inceptionV1

import torch.nn as nn
import torch
import torch.nn.functional as F

class GoogLeNet(nn.Module):
def __init__(self, num_classes=1000, aux_logits=True, init_weights=False):
super(GoogLeNet, self).init()

    self.aux_logits = aux_logits

    # 7\*7,stride=2
    self.conv1 = BasicConv2d(3, 64, kernel_size=7, stride=2, padding=3)
    self.maxpool1 = nn.MaxPool2d(3, stride=2, ceil_mode=True)

    # 1\*1+3\*3+maxpool
    self.conv2 = BasicConv2d(64, 64, kernel_size=1)
    self.conv3 = BasicConv2d(64, 192, kernel_size=3, padding=1)
    self.maxpool2 = nn.MaxPool2d(3, stride=2, ceil_mode=True)

    # 枝丫a
    self.inception3a = Inception(192, 64, 96, 128, 16, 32, 32)
    # 枝丫a
    self.inception3b = Inception(256, 128, 128, 192, 32, 96, 64)
    self.maxpool3 = nn.MaxPool2d(3, stride=2, ceil_mode=True)


    self.inception4a = Inception(480, 192, 96, 208, 16, 48, 64)
    self.inception4b = Inception(512, 160, 112, 224, 24, 64, 64)
    self.inception4c = Inception(512, 128, 128, 256, 24, 64, 64)
    self.inception4d = Inception(512, 112, 144, 288, 32, 64, 64)
    self.inception4e = Inception(528, 256, 160, 320, 32, 128, 128)
    self.maxpool4 = nn.MaxPool2d(3, stride=2, ceil_mode=True)

    self.inception5a = Inception(832, 256, 160, 320, 32, 128, 128)
    self.inception5b = Inception(832, 384, 192, 384, 48, 128, 128)

    # 辅助分类器
    if self.aux_logits:
        self.aux1 = InceptionAux(512, num_classes)
        self.aux2 = InceptionAux(528, num_classes)

    # 平均池化
    self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
    self.dropout = nn.Dropout(0.4)
    self.fc = nn.Linear(1024, num_classes)
    if init_weights:
        self._initialize_weights()

def forward(self, x):
    # N x 3 x 224 x 224
    x = self.conv1(x)
    # N x 64 x 112 x 112
    x = self.maxpool1(x)
    # N x 64 x 56 x 56
    x = self.conv2(x)
    # N x 64 x 56 x 56
    x = self.conv3(x)
    # N x 192 x 56 x 56
    x = self.maxpool2(x)

    # N x 192 x 28 x 28
    x = self.inception3a(x)
    # N x 256 x 28 x 28
    x = self.inception3b(x)
    # N x 480 x 28 x 28
    x = self.maxpool3(x)
    # N x 480 x 14 x 14
    x = self.inception4a(x)
    # N x 512 x 14 x 14
    if self.training and self.aux_logits:    # eval model lose this layer
        aux1 = self.aux1(x)

    x = self.inception4b(x)
    # N x 512 x 14 x 14
    x = self.inception4c(x)
    # N x 512 x 14 x 14
    x = self.inception4d(x)
    # N x 528 x 14 x 14

    if self.training and self.aux_logits:    # eval model lose this layer
        aux2 = self.aux2(x)

    x = self.inception4e(x)
    # N x 832 x 14 x 14
    x = self.maxpool4(x)
    # N x 832 x 7 x 7
    x = self.inception5a(x)
    # N x 832 x 7 x 7
    x = self.inception5b(x)
    # N x 1024 x 7 x 7

    x = self.avgpool(x)
    # N x 1024 x 1 x 1
    x = torch.flatten(x, 1)
    # N x 1024
    x = self.dropout(x)
    x = self.fc(x)
    # N x 1000 (num\_classes)
    if self.training and self.aux_logits:   # eval model lose this layer
        return x, aux2, aux1
    return x

def \_initialize\_weights(self):

    for m in self.modules():
        if isinstance(m, nn.Conv2d):
            nn.init.kaiming_normal_(m.weight, mode='fan\_out', nonlinearity='relu')
            if m.bias is not None:
                nn.init.constant_(m.bias, 0)
        elif isinstance(m, nn.Linear):
            nn.init.normal_(m.weight, 0, 0.01)
            nn.init.constant_(m.bias, 0)

class Inception(nn.Module):
def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):
‘’’

:param in_channels: 输入的通道数
:param ch1x1: 1x1 卷积核通道数
:param ch3x3red:
:param ch3x3:
:param ch5x5red:
:param ch5x5:
:param pool_proj: 池化输出通道
‘’’
super(Inception, self).init()

    self.branch1x1 = BasicConv2d(in_channels=in_channels,out_channels= ch1x1, kernel_size=1)

    self.branch3x3 = nn.Sequential(
        BasicConv2d(in_channels=in_channels, out_channels=ch3x3red, kernel_size=1),
        BasicConv2d(in_channels= ch3x3red, out_channels=ch3x3, kernel_size=3, padding=1)   # 保证输出大小等于输入大小
    )

    self.branch5x5 = nn.Sequential(
        BasicConv2d(in_channels=in_channels, out_channels=ch5x5red, kernel_size=1),
        BasicConv2d(in_channels=ch5x5red, out_channels=ch5x5, kernel_size=5, padding=2)   # 保证输出大小等于输入大小
    )

    self.pool = nn.Sequential(
        nn.MaxPool2d(kernel_size=3, stride=1, padding=1),
        BasicConv2d(in_channels=in_channels, out_channels=pool_proj, kernel_size=1)
    )

def forward(self, x):
    branch1 = self.branch1x1(x)
    branch2 = self.branch3x3(x)
    branch3 = self.branch5x5(x)
    branch4 = self.pool(x)

    outputs = [branch1, branch2, branch3, branch4]
    return torch.cat(outputs, 1)