王权富贵:
本文详细介绍了GoogLeNet网络结构及其核心组件Inception模块的设计原理与实现代码。通过PyTorch框架,从Inception模块的构建到整个GoogLeNet网络的搭建过程,展示了深度学习中模块化设计的重要性。
感谢kuangliu,参考自这个项目里面的一篇叫googlenet.py的文档。
先构建一个基本的Inception模块。构造如上图所示,具体代码如下所示。
'''GoogLeNet with PyTorch.'''import torchimport torch.nn as nnimport torch.nn.functional as F class Inception(nn.Module): def __init__(self, in_planes, n1x1, n3x3red, n3x3, n5x5red, n5x5, pool_planes): super(Inception, self).__init__() # 1x1 conv branch self.b1 = nn.Sequential( nn.Conv2d(in_planes, n1x1, kernel_size=1), nn.BatchNorm2d(n1x1), nn.ReLU(True), ) # 1x1 conv -> 3x3 conv branch self.b2 = nn.Sequential( nn.Conv2d(in_planes, n3x3red, kernel_size=1), nn.BatchNorm2d(n3x3red), nn.ReLU(True), nn.Conv2d(n3x3red, n3x3, kernel_size=3, padding=1), nn.BatchNorm2d(n3x3), nn.ReLU(True), ) # 1x1 conv -> 5x5 conv branch self.b3 = nn.Sequential( nn.Conv2d(in_planes, n5x5red, kernel_size=1), nn.BatchNorm2d(n5x5red), nn.ReLU(True), nn.Conv2d(n5x5red, n5x5, kernel_size=3, padding=1), nn.BatchNorm2d(n5x5), nn.ReLU(True), nn.Conv2d(n5x5, n5x5, kernel_size=3, padding=1), nn.BatchNorm2d(n5x5), nn.ReLU(True), ) # 3x3 pool -> 1x1 conv branch self.b4 = nn.Sequential( nn.MaxPool2d(3, stride=1, padding=1), nn.Conv2d(in_planes, pool_planes, kernel_size=1), nn.BatchNorm2d(pool_planes), nn.ReLU(True), )AI写代码python运行
GooLeNet的构建如下代码所示,对应结构图,在代码下面显示:
class GoogLeNet(nn.Module): def __init__(self): super(GoogLeNet, self).__init__() self.pre_layers = nn.Sequential( nn.Conv2d(3, 192, kernel_size=3, padding=1), nn.BatchNorm2d(192), nn.ReLU(True), ) self.a3 = Inception(192, 64, 96, 128, 16, 32, 32) self.b3 = Inception(256, 128, 128, 192, 32, 96, 64) self.maxpool = nn.MaxPool2d(3, stride=2, padding=1) self.a4 = Inception(480, 192, 96, 208, 16, 48, 64) self.b4 = Inception(512, 160, 112, 224, 24, 64, 64) self.c4 = Inception(512, 128, 128, 256, 24, 64, 64) self.d4 = Inception(512, 112, 144, 288, 32, 64, 64) self.e4 = Inception(528, 256, 160, 320, 32, 128, 128) self.a5 = Inception(832, 256, 160, 320, 32, 128, 128) self.b5 = Inception(832, 384, 192, 384, 48, 128, 128) self.avgpool = nn.AvgPool2d(8, stride=1) self.linear = nn.Linear(1024, 10) def forward(self, x): out = self.pre_layers(x) out = self.a3(out) out = self.b3(out) out = self.maxpool(out) out = self.a4(out) out = self.b4(out) out = self.c4(out) out = self.d4(out) out = self.e4(out) out = self.maxpool(out) out = self.a5(out) out = self.b5(out) out = self.avgpool(out) out = out.view(out.size(0), -1) out = self.linear(out) return outAI写代码python运行
Inception模块中通道的选取参考如下:
上面代码是简化版,它在开始部分没有经过一个7*7和1*1的卷积,直接从3*3开始。辅助分类器也没有写上。
点击查看更多内容
为 TA 点赞
评论
共同学习,写下你的评论
评论加载中...
作者其他优质文章
正在加载中
感谢您的支持,我会继续努力的~
扫码打赏,你说多少就多少
赞赏金额会直接到老师账户
支付方式
打开微信扫一扫,即可进行扫码打赏哦