GoogleNet网络详解

model

# GoogleNe亮点
# 引入了Inception结构 （融合不同尺度的特征信息）
# 使用1x1 的卷积核进行降维以及映射处理
# 添加两个辅助分类器帮助训练
# 丢弃全连接层，使用平均池化层（大大减少模型参数）
# AlexNet和VGG都只有一个输出层 GoogleNet有三个输出层（其中两个辅助分类层）
# 辅助分类层： 平均池化下采样 5x5filter和stride3 + conv 1x1 + FC + FC
# 为什么大多数人都不去使用googlenet 而去使用vgg
# vgg搭建比较方便 且Google NET 有两个辅助分类器 修改和训练比较麻烦
# 如果只针对分类 google net明显更优秀
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
    def __init__(self, num_classes=1000, aux_logits=True, init_weights=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)
        # ceil_mode 如果计算出的值为小数 TRUE为向上取整
        # 并没有什么用 Localrespnorm

        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)

        self.inception3a = Inception(192, 64, 96, 128, 16, 32, 32)  # 调用刚刚的模板 in_channels   。。。后面都是表格里的数据
        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)

        if self.aux_logits:
            self.aux1 = InceptionAux(512, num_classes)
            self.aux2 = InceptionAux(528, num_classes)

        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))  # 自适应的平均池化下采样操作 无论输入的高宽如何 都能得到指定的高和宽
        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)



# pool_proj为第四个分支上卷积核为1x1卷积核个数
class Inception(nn.Module):        # ch1x1为第一个分支中卷积核个数 ch3x3red为第二个分支上的卷积核大小为1x1的卷积核个数 # ch3x3 为第二个分支上卷积核大小为3x3的卷积核个数依次类推
    def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):
        super(Inception, self).__init__()
        # 分支1  且每个分支所得的特征矩阵高和宽必须相同
        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)   # 保证输出大小等于输入大小
        )

        self.branch3 = nn.Sequential(
            BasicConv2d(in_channels, ch5x5red, kernel_size=1),
            BasicConv2d(ch5x5red, ch5x5, kernel_size=5, padding=2)   # 保证输出大小等于输入大小
        )

        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)     # torch.cat 将四个分支合并   1为所需合并的维度（channels）


class InceptionAux(nn.Module):    # 定义辅助分类器
    def __init__(self, in_channels, num_classes):
        super(InceptionAux, self).__init__()
        self.averagePool = nn.AvgPool2d(kernel_size=5, stride=3)
        self.conv = BasicConv2d(in_channels, 128, kernel_size=1)  # output[batch, 128, 4, 4]

        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
        x = self.averagePool(x)
        # aux1: N x 512 x 4 x 4, aux2: N x 528 x 4 x 4
        x = self.conv(x)
        # N x 128 x 4 x 4
        x = torch.flatten(x, 1)
        x = F.dropout(x, 0.5, training=self.training)
        # N x 2048
        x = F.relu(self.fc1(x), inplace=True)
        x = F.dropout(x, 0.5, training=self.training)
        # N x 1024
        x = self.fc2(x)
        # N x num_classes
        return x


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(inplace=True)

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

train

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))])}

    train_dataset = datasets.ImageFolder(root="./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

    train_loader = torch.utils.data.DataLoader(train_dataset,
                                               batch_size=batch_size, shuffle=True,
                                               num_workers=0)

    validate_dataset = datasets.ImageFolder(root="./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=0)

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

    # test_data_iter = iter(validate_loader)
    # test_image, test_label = test_data_iter.next()

    # net = torchvision.models.googlenet(num_classes=5)
    # model_dict = net.state_dict()
    # pretrain_model = torch.load("googlenet.pth")
    # del_list = ["aux1.fc2.weight", "aux1.fc2.bias",
    #             "aux2.fc2.weight", "aux2.fc2.bias",
    #             "fc.weight", "fc.bias"]
    # pretrain_dict = {k: v for k, v in pretrain_model.items() if k not in del_list}
    # model_dict.update(pretrain_dict)
    # net.load_state_dict(model_dict)
    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 = 50
    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()         # 还要加上辅助分类器的损失
            logits, aux_logits2, aux_logits1 = net(images.to(device))
            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  # 论文中写的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

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

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

img = Image.open('5.jfif')
plt.imshow(img)
img = data_transform(img)
img = torch.unsqueeze(img, dim=0)




try:
    json_file = open('./class_indices.json', 'r')
    class_indict = json.load(json_file)
except Exception as e:
    print(e)
    print(-1)


model = GoogLeNet(num_classes=5, aux_logits=False)
model_weight_path = './googleNet.pth'
missing_keys, unexpected_keys = model.load_state_dict(torch.load(model_weight_path), strict=False)
model.eval()
with torch.no_grad():
    output = torch.squeeze(model(img))
    predict = torch.softmax(output, dim=0)
    predict_cla = torch.argmax(predict).numpy()
# print(class_indict[str(predict_cla)])
print_res = "class: {}   prob: {:.3}".format(class_indict[str(predict_cla)],
                                                 predict[predict_cla].numpy())
plt.title(print_res)
print(print_res)
plt.show()