【学习笔记】GoogleNet 网络结构

跟着大佬学图像分类系列，→ 传送门 ←

本博客图像分类系列文章传送门：

AlexNet
VGG
GoogleNet（当前）
ResNet

---

前言

图像分类是学习目标检测的“量变”内容，那么，废话不多说，开搞！

---

一、GoogleNet 是什么？

        GoogleNet 网络是14年由 Google 团队提出，斩获该年 ImageNet 竞赛中 Classification Task（分类任务）第一名（刚学的VGG 是第二，哈哈）。

GoogleNet 论文的 → 传送门 ←

二、网络结构

1.网络特点

• 引入了 Inception 结构（融合不同尺度的特征信息）
• 使用 1*1 的卷积核进行降维以及映射处理

        左图为 Inception 结果的初始版本。从图中可以看出，之前学的网络，卷积层之间、卷积层和池化层之间是串联结构，而这里是并联结构。而右图增减了三个 1*1 的卷积核，使得特征矩阵的深度降低，极大的减少了参数，进而减少了计算量。

• 添加两个辅助分类器帮助训练
  （4a）和（4d ）旁边的结构

• 丢弃全连接层，而使用平均池化层（这大大的减少了模型参数）

2.结构

（参数说明）

列名	含义
type	网络中每层的结构名
patch size / stride	结构的参数（以第一行为例，结构为卷积层，卷积核大小为 7*7，步长为2）
output size	输出的特征矩阵的大小
depth	该行对应的结构有几个（以第三行为例，结构为卷积层，depth=2，表示经过两层卷积层（可对照论文中的网络结构来看，由于图太长，所以没贴，网络结构图是论文中的 Figure 3））
后8列	Inception 结构的一些配置

（如图所示，列名为 #1x1 的结构表示 Inception 中的 1x1 convolutions，对应行中的数字为卷积核的数量）

三、使用 Pytorch 搭建 GoogleNet 网络

本代码使用的数据集来自 “花分类” 数据集，→ 传送门 ←（具体内容看 data_set文件夹下的 README.md）

• model.py （ 搭建 GoogleNet 网络模型 ）

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


class GoogleNet(nn.Module):
    # aux_logits: 是否使用辅助分类器（训练的时候为True, 验证的时候为False)
    def __init__(self, num_classes=1000, aux_logits=True, init_weight=False):
        super(GoogleNet, self).__init__()
        self.aux_logits = aux_logits

        self.conv1 = BasicConv2d(3, 64, kernel_size=7, stride=2, padding=3)
        self.maxpool1 = nn.MaxPool2d(3, stride=2, ceil_mode=True)   # 当结构为小数时，ceil_mode=True向上取整，=False向下取整
        # nn.LocalResponseNorm （此处省略）
        self.conv2 = nn.Sequential(
            BasicConv2d(64, 64, kernel_size=1),
            BasicConv2d(64, 192, kernel_size=3, padding=1)
        )
        self.maxpool2 = nn.MaxPool2d(3, stride=2, ceil_mode=True)

        self.inception3a = Inception(192, 64, 96, 128, 16, 32, 32)
        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(2, 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)

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

        self.avgpool = nn.AdaptiveAvgPool1d((1, 1))
        self.dropout = nn.Dropout(0.4)
        self.fc = nn.Linear(1024, num_classes)

        if init_weight:
            self._initialize_weight()

    def forward(self, x):
        x = self.conv1(x)
        x = self.maxpool1(x)
        x = self.conv2(x)
        x = self.maxpool2(x)

        x = self.inception3a(x)
        x = self.inception3b(x)
        x =self.maxpool3(x)

        x =self.inception4a(x)
        if self.training and self.aux_logits:
            aux1 = self.aux1(x)
        x = self.inception4b(x)
        x = self.inception4c(x)
        x = self.inception4d(x)
        if self.training and self.aux_logits:
            aux2 = self.aux2(x)
        x = self.inception4e(x)
        x =self.maxpool4(x)

        x = self.inception5a(x)
        x = self.inception5b(x)

        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        x = self.dropout(x)
        x = self.fc(x)

        if self.training and self.aux_logits:
            return x, aux1, aux2
        return x


    def _initialize_weight(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='')
                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)






# 创建 Inception 结构函数（模板）
class Inception(nn.Module):
    # 参数为 Inception 结构的那几个卷积核的数量（详细见表）
    def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):
        super(Inception, self).__init__()
        # 四个并联结构
        self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)
        self.branch2 = nn.Sequential(
            BasicConv2d(in_channels, ch3x3red, kernel_size=1),
            BasicConv2d(ch3x3red, ch3x3, kernel_size=3, padding=1)
        )
        self.branch3 = nn.Sequential(
            BasicConv2d(in_channels, ch5x5red, kernel_size=1),
            BasicConv2d(ch5x5red, ch5x5, kernel_size=5, padding=2)
        )
        self.branch4 = nn.Sequential(
            nn.MaxPool2d(kernel_size=3, stride=1, padding=1),
            BasicConv2d(in_channels, pool_proj, kernel_size=1)
        )

    def forward(self, x):
        branch1 = self.branch1(x)
        branch2 = self.branch2(x)
        branch3 = self.branch3(x)
        branch4 = self.branch4(x)
        outputs = [branch1, branch2, branch3, branch4]
        return torch.cat(outputs, 1)


# 创建辅助分类器结构函数（模板）
class InceptionAux(nn.Module):
    def __init__(self, in_channels, num_classes):
        super(InceptionAux, self).__init__()
        self.avgPool = nn.AvgPool2d(kernel_size=5, stride=3)
        self.conv = BasicConv2d(in_channels, 128, kernel_size=1)

        self.fc1 = nn.Linear(2048, 1024)
        self.fc2 = nn.Linear(1024, num_classes)

    def forward(self, x):
        # aux1: N x 512 x 14 x 14   aux2: N x 528 x 14 x 14（输入）
        x = self.avgPool(x)
        # aux1: N x 512 x 4 x 4  aux2: N x 528 x 4 x 4（输出） 4 = (14 - 5)/3 + 1
        x = self.conv(x)
        x = torch.flatten(x, 1)     # 展平
        x = F.dropout(x, 0.5, training=self.training)
        x = F.relu(self.fc1(x), inplace=True)
        x = F.dropout(x, 0.5, training=self.training)
        x = self.fc2(x)
        return x


# 创建卷积层函数（模板）
class BasicConv2d(nn.Module):
    def __init__(self, in_channels, out_channels, **kwargs):
        super(BasicConv2d, self).__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, **kwargs)
        self.relu = nn.ReLU(True)

    def forward(self, x):
        x = self.conv(x)
        x = self.relu(x)
        return x

• train.py （ 训练网络 ）

import os
import json

import torch
import torch.nn as nn
from torchvision import transforms, datasets
import torch.optim as optim
from tqdm import tqdm

from model import GoogleNet


def main():
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    print("using {} device.".format(device))

    data_transform = {
        "train": transforms.Compose([transforms.RandomResizedCrop(224),
                                     transforms.RandomHorizontalFlip(),
                                     transforms.ToTensor(),
                                     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]),
        "val": transforms.Compose([transforms.Resize((224, 224)),
                                   transforms.ToTensor(),
                                   transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])}

    data_root = os.path.abspath(os.path.join(os.getcwd(), "../.."))  # get data root path
    image_path = os.path.join(data_root, "data_set", "flower_data")  # flower data set path
    assert os.path.exists(image_path), "{} path does not exist.".format(image_path)
    train_dataset = datasets.ImageFolder(root=os.path.join(image_path, "train"),
                                         transform=data_transform["train"])
    train_num = len(train_dataset)

    # {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
    flower_list = train_dataset.class_to_idx
    cla_dict = dict((val, key) for key, val in flower_list.items())
    # write dict into json file
    json_str = json.dumps(cla_dict, indent=4)
    with open('class_indices.json', 'w') as json_file:
        json_file.write(json_str)

    batch_size = 32
    nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8])  # number of workers
    print('Using {} dataloader workers every process'.format(nw))

    train_loader = torch.utils.data.DataLoader(train_dataset,
                                               batch_size=batch_size, shuffle=True,
                                               num_workers=nw)

    validate_dataset = datasets.ImageFolder(root=os.path.join(image_path, "val"),
                                            transform=data_transform["val"])
    val_num = len(validate_dataset)
    validate_loader = torch.utils.data.DataLoader(validate_dataset,
                                                  batch_size=batch_size, shuffle=False,
                                                  num_workers=nw)

    print("using {} images for training, {} images for validation.".format(train_num,
                                                                           val_num))


    net = GoogleNet(num_classes=5, aux_logits=True, init_weights=True)
    net.to(device)
    loss_function = nn.CrossEntropyLoss()
    optimizer = optim.Adam(net.parameters(), lr=0.0003)

    epochs = 30
    best_acc = 0.0
    save_path = './googleNet.pth'
    train_steps = len(train_loader)
    for epoch in range(epochs):
        # train
        net.train()
        running_loss = 0.0
        train_bar = tqdm(train_loader)
        for step, data in enumerate(train_bar):
            images, labels = data
            optimizer.zero_grad()
            logits, aux_logits2, aux_logits1 = net(images.to(device))   # 由于训练的时候会使用辅助分类器，所有相当于有三个返回结果
            loss0 = loss_function(logits, labels.to(device))
            loss1 = loss_function(aux_logits1, labels.to(device))
            loss2 = loss_function(aux_logits2, labels.to(device))
            loss = loss0 + loss1 * 0.3 + loss2 * 0.3
            loss.backward()
            optimizer.step()

            # print statistics
            running_loss += loss.item()

            train_bar.desc = "train epoch[{}/{}] loss:{:.3f}".format(epoch + 1,
                                                                     epochs,
                                                                     loss)

        # validate
        net.eval()
        acc = 0.0  # accumulate accurate number / epoch
        with torch.no_grad():
            val_bar = tqdm(validate_loader)
            for val_data in val_bar:
                val_images, val_labels = val_data
                outputs = net(val_images.to(device))  # eval model only have last output layer
                predict_y = torch.max(outputs, dim=1)[1]
                acc += torch.eq(predict_y, val_labels.to(device)).sum().item()

        val_accurate = acc / val_num
        print('[epoch %d] train_loss: %.3f  val_accuracy: %.3f' %
              (epoch + 1, running_loss / train_steps, val_accurate))

        if val_accurate > best_acc:
            best_acc = val_accurate
            torch.save(net.state_dict(), save_path)

    print('Finished Training')


if __name__ == '__main__':
    main()

• predict.py （ 使用训练好的模型网络对图像分类 ）

import os
import json

import torch
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt

from model import GoogleNet


def main():
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

    data_transform = transforms.Compose(
        [transforms.Resize((224, 224)),
         transforms.ToTensor(),
         transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

    # load image
    img_path = "../tulip.jpg"
    assert os.path.exists(img_path), "file: '{}' dose not exist.".format(img_path)
    img = Image.open(img_path)
    plt.imshow(img)
    # [N, C, H, W]
    img = data_transform(img)
    # expand batch dimension
    img = torch.unsqueeze(img, dim=0)

    # read class_indict
    json_path = './class_indices.json'
    assert os.path.exists(json_path), "file: '{}' dose not exist.".format(json_path)

    json_file = open(json_path, "r")
    class_indict = json.load(json_file)

    # create model
    model = GoogleNet(num_classes=5, aux_logits=False).to(device)

    # load model weights
    weights_path = "./googleNet.pth"
    assert os.path.exists(weights_path), "file: '{}' dose not exist.".format(weights_path)
    missing_keys, unexpected_keys = model.load_state_dict(torch.load(weights_path, map_location=device),
                                                          strict=False)

    model.eval()
    with torch.no_grad():
        # predict class
        output = torch.squeeze(model(img.to(device))).cpu()
        predict = torch.softmax(output, dim=0)
        predict_cla = torch.argmax(predict).numpy()

    print_res = "class: {}   prob: {:.3}".format(class_indict[str(predict_cla)],
                                                 predict[predict_cla].numpy())
    plt.title(print_res)
    print(print_res)
    plt.show()


if __name__ == '__main__':
    main()

代码连接 https://github.com/WZMIAOMIAO/deep-learning-for-image-processing/tree/master/pytorch_classification/Test4_googlenet