第J9周：Inception v3算法实战与解析

• 🍨 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
  

电脑环境：
语言环境：Python 3.8.0
深度学习环境：torch 2.5.1+cu121

一、前言

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lmageNet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的卷积核。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1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，帮助网络更好地学习特征。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。

二、代码流程

1、导入包，设置GPU

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
import torch.nn.functional as F
from torchvision import transforms, datasets
import os, PIL, pathlib

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device

2、导入数据

data_dir = './data/'
data_dir = pathlib.Path(data_dir)

data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("/")[-1] for path in data_paths]
classeNames

‘cloudy’, ‘sunrise’, ‘shine’, ‘rain’]

3、数据处理

train_transforms = transforms.Compose([
    transforms.Resize([299, 299]),
    transforms.ToTensor(),
    transforms.Normalize(
        mean=[0.485, 0.456, 0.406],
        std=[0.229, 0.224, 0.225])
])

total_data = datasets.ImageFolder(data_dir,transform=train_transforms)

train_size = int(0.8 * len(total_data))
test_size = len(total_data) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size])
len(train_dataset), len(test_dataset)

(904, 226)

batch_size = 32

train_dl = torch.utils.data.DataLoader(train_dataset,
                                       batch_size=batch_size,
                                       shuffle=True)
test_dl = torch.utils.data.DataLoader(test_dataset,
                                      batch_size=batch_size,
                                      shuffle=True)

4、设置网络

Inception-A

'''---InceptionA---'''
class InceptionA(nn.Module):

    def __init__(self, in_channels, pool_features):
        super(InceptionA, self).__init__()

        self.branch1x1 = BasicConv2d(in_channels, 64, kernel_size=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)

Inception-B

'''---InceptionB---'''
class InceptionB(nn.Module):

    def __init__(self, in_channels, channels_7x7):
        super(InceptionB, self).__init__()
        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=