【论文阅读】GoogLeNet——Going Deeper with Convolutions

论文阅读

感谢P导

Going Deeper with Convolutions

网络中的亮点:

引入了Inception结构（融合不同尺度的特征信息)
每个分支得到的特征矩阵宽和高必须相同(padding、stride)，之后延深度拼接
每个Inception的输入长宽和输出长宽也是一致的
1、based on the Hebbian principle(neurons that fire together,wire together) and the intuition of multi-scale processing
2、Network-in-Network

使用1x1的卷积核进行降维以及映射处理，如果不使用1*1的进行降维处理，按照传统惯例，在进行卷积之后升维，多个输出结果进行concatenate会造成通道数的越来越多，先降维，之后使用卷积升维之后不会造成太多的通道数，减少计算量

添加两个辅助分类器帮助训练（三个输出节点，只在训练阶段使用计算loss）
GoogLeNet的Inception V1时期没有ResNet，防止梯度消失，网络层数太深，最后一层的结果无法调整底层的参数

丢弃全连接层，使用平均池化层（大大减少模型参数）

模型图示

模型图为模型在预测1张图片时候使用tensorboard输出的图片，代码中有对应操作，不需要的可以删除

代码实现

model

定义一个basicConv2d，因为每次卷积之后都会接激活函数，每次都写，太多

定义Inception模块，根据论文中的架构表，可以看到，Inception需要传入的参数只有in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj，第一个是输入通道数，后面的都是各层的输出通道数，要保证每层输出的特征图长宽一致，需要进行计算padding、stride

定义辅助分类器，根据上面辅助分类器详解

定义GoogLeNet

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


class GoogLeNet(nn.Module):
    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)

        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)
        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))
        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:   
            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:    
            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时候不需要返回辅助分类器
            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)

# 每个Inception模块的输入长宽和输出长宽一样，每个分支的输出也要相同
class Inception(nn.Module):
    def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):
        super(Inception, self).__init__()

        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)#对应channel位置进行拼接


class InceptionAux(nn.Module):
    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)
        x = torch.flatten(x, 1)
        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

# conv模板，输入深度，输出深度
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))])}

    data_root = os.path.abspath(os.path.join(os.getcwd(), "../"))  # get data root path
    image_path = os.path.join(data_root,  "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"])
    validate_dataset = datasets.ImageFolder(root=os.path.join(image_path, "val"),
                                            transform=data_transform["val"])
    
    train_num = len(train_dataset)
    val_num = len(validate_dataset)
    print("using {} images for training, {} images for validation.".format(train_num,
                                                                           val_num))
    
    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 = 16
    nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8])  
    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_loader = torch.utils.data.DataLoader(validate_dataset,
                                                  batch_size=batch_size, shuffle=False,
                                                  num_workers=nw)

    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 data in train_bar:
            images, labels = data
            optimizer.zero_grad()
            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 # 0.3权重
            loss.backward()
            optimizer.step()

            running_loss += loss.item()

            train_bar.desc = "train epoch[{}/{}] loss:{:.3f}".format(epoch + 1,
                                                                     epochs,
                                                                     loss)
        #eval
        net.eval()
        acc = 0.0  
        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 os
import json

import torch
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt
from torch.utils.tensorboard import SummaryWriter, writer
from model import GoogLeNet


def main():
    writer=SummaryWriter('logs')
    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))])

    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)    
    img = data_transform(img)
    img = torch.unsqueeze(img, dim=0)# 添加维度

    # 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
        writer.add_graph(model,img.to(device))
        writer.close()
        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()

实验结果