J9 Inception v3算法实战

weixin_46559155

于 2024-03-30 00:00:55 发布

阅读量887

点赞数 25

文章标签：深度学习人工智能

本文链接：https://blog.csdn.net/weixin_46559155/article/details/137159434

版权

🍨 本文为🔗365天深度学习训练营中的学习记录博客
🍖 原作者：K同学啊|接辅导、项目定制

1 理论基础

Inception v3由谷歌研究员Christian Szegedy等人在2015年的论文《Rethinking the Inception Architecture for Computer Vision》中提出。Inception v3是Inception网络系列的第三个版本，它在ImageNet图像识别竞赛中取得了优异成绩，尤其是在大规模图像识别任务中表现出色。
Inception v3的主要特点如下：
1、更深的网络结构：Inception v3比之前的Inception网络结构更深，包含了48层卷积层。这使得网络可以提取更多层次的特征，从而在图像识别任务上取得更好的效果。
2、使用Factorized Convolutions：Inception v3采用了Factorized Convolutions（分解卷积），将较大的卷积核分解为多个较小卷积核。这种方法可以降低网络的参数数量，减少计算复杂度，同时保持良好的性能。
3、使用Batch Normalization：Inception v3在每个卷积层之后都添加了Batch Normalization（BN），这有助于网络的收敛和泛化能力。BN可以减少Internal Covariate Shift（内部协变量偏移）现象，加快训练速度，同时提高模型的鲁棒性。
4、辅助分类器：Inception v3引入了辅助分类器，可以在网络训练过程中提供额外的梯度信息，帮助网络更好的学习特征。辅助分类器位于网络的某个中间层，其输出会与主分类器的输出进行加权融合，从而得到最终的预测结果。
5、基于RMSProp的优化器：Inception v3使用了RMSProp优化器进行训练。相比于传统的随机梯度下降（SGD）方法，RMSProp可以自适应地调整学习率，使得训练过程更加稳定，收敛速度更快。
Inception v3在图像分类、物体检测和图像分割等计算机视觉任务中均取得了显著的效果。然而，由于其较大的网络结构和计算复杂度，Inception v3在实际应用中可能需要较高的硬件要求。
相对于Inception v1的Inception Module结构，Inception v3中做出了如下改动：
（1）将5x5的卷积分解为两个3x3的卷积运算已提升计算速度。尽管这有点违反直觉，但一个5x5的卷积在计算成本上是一个3x3卷积的2.78倍。所以叠加两个3x3卷积实际上在性能上会有所提升，如下图所示：

（2）此外，作者将nxn的卷积核尺寸分解为1xn和nx1两个卷积，例如，一个3x3的卷积等价于首先执行一个1x3的卷积，再执行一个3x1的卷积。他们还发现这种方法在成本上要比单个3x3的卷积降低33%，这一结构如下图所示：

此处如果n=3，则与上一张图像一致。最左侧的5x5卷积可被表示为两个3x3卷积，太慢又可以表示为1x3和3x1卷积。
模块中的滤波器组被扩展（即变得更宽而不是更深），以解决表征性瓶颈。如果该模块没有被拓展宽度，而是变得更深，那么维度会过多减少，造成信息损失。如下图所示：

最后实现的inception v3网络是如下所示：

2Inception v3的实现

2.1Inception-A

import torch
import torch.nn as nn
import torch.nn.functional as F
 
class BasicConv2d(nn.Module):
    def __init__(self, in_channels, out_channels, **kwargs):
        super(BasicConv2d, self).__init__()
        
        self.conv = nn.Conv2d(in_channels, out_channels, bias=False, **kwargs)
        self.bn = nn.BatchNorm2d(out_channels, eps=0.001)
        
    def forward(self, x):
        x = self.conv(x)
        x = self.bn(x)
        return F.relu(x, inplace=True)
        
class InceptionA(nn.Module):
    def __init__(self, in_channels, pool_features):
        super(InceptionA, self).__init__()
        
        # 1x1 conv branch
        self.branch1x1 = BasicConv2d(in_channels, 64, kernel_size=1) #1
        
        self.branch5x5_1 = BasicConv2d(in_channels, 48, kernel_size=1)
        self.branch5x5_2 = BasicConv2d(48, 64, kernel_size=5, padding=2)
        
        self.branch3x3dbl_1 = BasicConv2d(in_channels, 64, kernel_size=1)
        self.branch3x3dbl_2 = BasicConv2d(64, 96, kernel_size=3, padding=1)
        self.branch3x3dbl_3 = BasicConv2d(96, 96, kernel_size=3, padding=1)
        
        self.branch_pool = BasicConv2d(in_channels, pool_features, kernel_size=1)
        
    def forward(self, x):
        branch1x1 = self.branch1x1(x)
        
        branch5x5 = self.branch5x5_1(x)
        branch5x5 = self.branch5x5_2(branch5x5)
        
        branch3x3dbl = self.branch3x3dbl_1(x)
        branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
        branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl)
        
        branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)
        
        outputs = [branch1x1, branch5x5, branch3x3dbl, branch_pool]
        return torch.cat(outputs, 1)

2.2 Inception-B

class InceptionB(nn.Module):
    def __init__(self, in_channels, channels_7x7):
        super(InceptionB, self).__init__()
        
        # 1x1 conv branch
        self.branch1x1 = BasicConv2d(in_channels, 192, kernel_size=1)
        
        c7 = channels_7x7
        self.branch7x7_1 = BasicConv2d(in_channels, c7, kernel_size=1)
        self.branch7x7_2 = BasicConv2d(c7, c7, kernel_size=(1,7), padding=(0,3))
        self.branch7x7_3 = BasicConv2d(c7, 192, kernel_size=(7,1), padding=(3,0))
        
        self.branch7x7dbl_1 = BasicConv2d(in_channels, c7, kernel_size=1)
        self.branch7x7dbl_2 = BasicConv2d(c7, c7, kernel_size=(7,1), padding=(3,0))
        self.branch7x7dbl_3 = BasicConv2d(c7, c7, kernel_size=(1,7), padding=(0,3))
        self.branch7x7dbl_4 = BasicConv2d(c7, c7, kernel_size=(7,1), padding=(3,0))
        self.branch7x7dbl_5 = BasicConv2d(c7, 192, kernel_size=(1,7), padding=(0,3))
        
        self.branch_pool = BasicConv2d(in_channels, 192, kernel_size=1)
        
    def forward(self, x):
        branch1x1 = self.branch1x1(x)
        
        branch7x7 = self.branch7x7_1(x)
        branch7x7 = self.branch7x7_2(branch7x7)
        branch7x7 = self.branch7x7_3(branch7x7)
        
        branch7x7dbl = self.branch7x7dbl_1(x)
        branch7x7dbl = self.branch7x7dbl_2(branch7x7dbl)
        branch7x7dbl = self.branch7x7dbl_3(branch7x7dbl)
        branch7x7dbl = self.branch7x7dbl_4(branch7x7dbl)
        branch7x7dbl = self.branch7x7dbl_5(branch7x7dbl)
        
        branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)
        
        outputs = [branch1x1, branch7x7, branch7x7dbl, branch_pool]
        return torch.cat(outputs, 1)

2.3 Inception-C

class InceptionC(nn.Module):
    def __init__(self, in_channels):
        super(InceptionC, self).__init__()
        
        self.branch1x1 = BasicConv2d(in_channels, 320, kernel_size=1) #1
        
        self.branch3x3_1 = BasicConv2d(in_channels, 384, kernel_size=1)
        self.branch3x3_2a = BasicConv2d(384, 384, kernel_size=(1,3), padding=(0,1))
        self.branch3x3_2b = BasicConv2d(384, 384, kernel_size=(3,1), padding=(1,0))
        
        self.branch3x3dbl_1 = BasicConv2d(in_channels, 448, kernel_size=1)
        self.branch3x3dbl_2 = BasicConv2d(448, 384, kernel_size=3, padding=1)
        self.branch3x3dbl_3a = BasicConv2d(384, 384, kernel_size=(1,3), padding=(0,1))
        self.branch3x3dbl_3b = BasicConv2d(384, 384, kernel_size=(3,1), padding=(1,0))
        
        self.branch_pool = BasicConv2d(in_channels, 192, kernel_size=1)
        
    def forward(self, x):
        branch1x1 = self.branch1x1(x)
        
        branch3x3 = self.branch3x3_1(x)
        branch3x3 = [self.branch3x3_2a(branch3x3),
                     self.branch3x3_2b(branch3x3),
                    ]
        branch3x3 = torch.cat(branch3x3, 1)
        
        branch3x3dbl = self.branch3x3dbl_1(x)
        branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
        branch3x3dbl = [self.branch3x3dbl_3a(branch3x3dbl),
                        self.branch3x3dbl_3b(branch3x3dbl),
                       ]
        branch3x3dbl = torch.cat(branch3x3dbl, 1)
        
        branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)
        
        outputs = [branch1x1, branch3x3, branch3x3dbl, branch_pool]
        return torch.cat(outputs, 1)

2.4 Reduction-A

class ReductionA(nn.Module):
    def __init__(self, in_channels):
        super(ReductionA, self).__init__()
        
        self.branch3x3 = BasicConv2d(in_channels, 384, kernel_size=3, stride=2) 
        
        self.branch3x3dbl_1 = BasicConv2d(in_channels, 64, kernel_size=1)
        self.branch3x3dbl_2 = BasicConv2d(64, 96, kernel_size=3, padding=1)
        self.branch3x3dbl_3 = BasicConv2d(96, 96, kernel_size=3, stride=2)
                
    def forward(self, x):
        branch3x3 = self.branch3x3(x)
        
        branch3x3dbl = self.branch3x3dbl_1(x)
        branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
        branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl)
        
        branch_pool = F.max_pool2d(x, kernel_size=3, stride=2)
        
        outputs = [branch3x3, branch3x3dbl, branch_pool]
        return torch.cat(outputs, 1)

2.5 Reduction-B

class ReductionB(nn.Module):
    def __init__(self, in_channels):
        super(ReductionB, self).__init__()
        
        self.branch3x3_1 = BasicConv2d(in_channels, 192, kernel_size=1) 
        self.branch3x3_2 = BasicConv2d(192, 320, kernel_size=3, stride=2) 
        
        self.branch7x7x3_1 = BasicConv2d(in_channels, 192, kernel_size=1)
        self.branch7x7x3_2 = BasicConv2d(192, 192, kernel_size=(1,7), padding=(0,3))
        self.branch7x7x3_3 = BasicConv2d(192, 192, kernel_size=(7,1), padding=(3,0))
        self.branch7x7x3_4 = BasicConv2d(192, 192, kernel_size=3, stride=2)
                
    def forward(self, x):
        branch3x3 = self.branch3x3_1(x)
        branch3x3 = self.branch3x3_2(branch3x3)
        
        branch7x7x3 = self.branch7x7x3_1(x)
        branch7x7x3 = self.branch7x7x3_2(branch7x7x3)
        branch7x7x3 = self.branch7x7x3_3(branch7x7x3)
        branch7x7x3 = self.branch7x7x3_4(branch7x7x3)
        
        branch_pool = F.max_pool2d(x, kernel_size=3, stride=2)
        
        outputs = [branch3x3, branch7x7x3, branch_pool]
        return torch.cat(outputs, 1)

2.6 辅助分支

class InceptionAux(nn.Module):
    def __init__(self, in_channels, num_classes):
        super(InceptionAux, self).__init__()
        
        self.conv0 = BasicConv2d(in_channels, 128, kernel_size=1)
        self.conv1 = BasicConv2d(128, 768, kernel_size=5)
        self.conv1.stddev = 0.01
        self.fc = nn.Linear(768, num_classes)
        self.fc.stddev = 0.001
                   
    def forward(self, x):
        # 17x17x768
        x = F.avg_pool2d(x, kernel_size=5, stride=3)
        # 5x5x768
        x = self.conv0(x)
        # 5x5x128
        x = self.conv1(x)
        # 1x1x128
        x = x.view(x.size(0), -1)
        # 768
        x = self.fc(x)
        # num_classes
        return x

2.7 模型搭建

class InceptionV3(nn.Module):
    def __init__(self, num_classes=1000, aux_logits=False, transform_input=False):
        super(InceptionV3, self).__init__()
        
        self.aux_logits = aux_logits
        self.transform_input = transform_input
        
        self.conv2d_1a_3x3 = BasicConv2d(3, 32, kernel_size=3, stride=2)
        self.conv2d_2a_3x3 = BasicConv2d(32, 32, kernel_size=3)
        self.conv2d_2b_3x3 = BasicConv2d(32, 64, kernel_size=3, padding=1)
        self.conv2d_3b_1x1 = BasicConv2d(64, 80, kernel_size=1)
        self.conv2d_4a_3x3 = BasicConv2d(80, 192, kernel_size=3)
        
        self.Mixed_5b = InceptionA(192, pool_features=32)
        self.Mixed_5c = InceptionA(256, pool_features=64)
        self.Mixed_5d = InceptionA(288, pool_features=64)
        self.Mixed_6a = ReductionA(288)
        self.Mixed_6b = InceptionB(768, channels_7x7=128)
        self.Mixed_6c = InceptionB(768, channels_7x7=160)
        self.Mixed_6d = InceptionB(768, channels_7x7=160)
        self.Mixed_6e = InceptionB(768, channels_7x7=192)
        
        if aux_logits:
            self.AuxLogits = InceptionAux(768, num_classes)
        self.Mixed_7a = ReductionB(768)
        self.Mixed_7b = InceptionC(1280)
        self.Mixed_7c = InceptionC(2048)
        
        self.fc = nn.Linear(2048, num_classes)
                               
    def forward(self, x):
        if self.transform_input:
            x = x.clone()
            x[:, 0] = x[:, 0] * (0.229 / 0.5) + (0.485 - 0.5) / 0.5
            x[:, 1] = x[:, 1] * (0.224 / 0.5) + (0.456 - 0.5) / 0.5
            x[:, 2] = x[:, 2] * (0.225 / 0.5) + (0.406 - 0.5) / 0.5
            
        # 299*299*3
        x = self.conv2d_1a_3x3(x)
        # 149*149*32
        x = self.conv2d_2a_3x3(x)
        # 147*147*32
        x = self.conv2d_2b_3x3(x)
        # 147*147*64
        x = F.max_pool2d(x, kernel_size=3, stride=2)
        # 73*73*64
        x = self.conv2d_3b_1x1(x)
        # 73*73*80
        x = self.conv2d_4a_3x3(x)
        # 71*71*192
        x = F.max_pool2d(x, kernel_size=3, stride=2)
        # 35*35*192
        x = self.Mixed_5b(x)
        # 35*35*256
        x = self.Mixed_5c(x)
        # 35*35*288
        x = self.Mixed_5d(x)
        # 35*35*288
        x = self.Mixed_6a(x)
        # 17*17*768
        x = self.Mixed_6b(x)
        # 17*17*768
        x = self.Mixed_6c(x)
        # 17*17*768
        x = self.Mixed_6d(x)
        # 17*17*768
        x = self.Mixed_6e(x)
        
        # 17*17*768
        if self.training and self.aux_logits:
            aux = self.AuxLogits(x)
        # 17*17*768
        x = self.Mixed_7a(x)
        # 8*8*1280
        x = self.Mixed_7b(x)
        # 8*8*2048
        x = self.Mixed_7c(x)
        
        # 8*8*2048
        x = F.avg_pool2d(x, kernel_size=8)
        # 1*1*2048
        x = F.dropout(x, training=self.training)
        # 1*1*2048
        x = x.view(x.size(0), -1)
        # 2048
        x = self.fc(x)
        # num_classes
        if self.training and self.aux_logits:
            return x, aux
        
        return x

2.8 查看模型详情

# 统计模型参数量以及其他指标
import torchsummary
 
# 调用并将模型转移到GPU中
model = InceptionV3().to(device)
 
# 显示网络结构
torchsummary.summary(model, (3, 299, 299))
print(model)

输出结果如下（由于内容较多，只展示前后部分内容）：