pytorch学习（六）—— MobileNet网络搭建

本篇博客是学习B站霹雳吧啦Wz教学视频的总结

本节所用到的程序和教学视频链接：

程序
视频
数据集下载，提取码:dw2d

---

MobileNet V1网络结构

在移动设备中运行深度学习

• 轻量级CNN网络，牺牲少量准确率来大大减少模型参数与运算量

• 提出了Depthwise Convolution+Pointwise Convolution 大大减少运算量(理论上普通卷积计算量是DW+PW的8到9倍)

  • DW卷积（Depthwish Cov）
    • 卷积核的深度为1
    • 输入特征矩阵channel=卷积核的个数=输出特征矩阵channel
      
    • 这种运算对输入层的每个通道独立进行卷积运算，没有有效的利用不同通道在相同空间位置上的feature信息。因此需要Pointwise Convolution来将这些Feature map进行组合生成新的Feature map。¹
  • PW卷积（Pointwise Conv）
    
    • Filter 和普通的卷积相同，只是大小为$1\times 1$

• 增加超参数**$\alpha 、\beta$**

---

MobileNet V2 网络结构

• Inverted Residuals（倒残差结构）

  • $1\times 1$卷积升维
  • $3\times 3$ DW卷积
  • $1\times 1$卷积升维
  • 使用ReLU6激活函数
    • $y=ReLU6(x)=min(max(x,0),6)$，而ReLU为：$max(x,0)$，相比较于ReLU，ReLU6有了上限
      
    • 最后一个卷积层使用线性激活函数 ,ReLu函数在会丢失低维特征
      
  • 当stride=1且输入特征矩阵与输出特征矩阵shape相同时才有shortcut连接（左图）
  • 上述就是网络中的Bottleneck layer 结构

• mobileNet网络的整体结构
  

  • t是一个扩展因子，来将反残差结构的第二个卷积层的特征矩阵的输入深度扩展到tk(k是输入网络的深度)
  • c控制输出通道数
  • n 是结构重复的次数
  • s 每个Bottleneck layer的第一个bottleneck的步距

---

程序

model.py

from torch import nn
import torch


def _make_divisible(ch, divisor=8, min_ch=None):
    """
    This function is taken from the original tf repo.
    It ensures that all layers have a channel number that is divisible by 8
    It can be seen here:
    https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
    """
    if min_ch is None:
        min_ch = divisor
    new_ch = max(min_ch, int(ch + divisor / 2) // divisor * divisor)
    # Make sure that round down does not go down by more than 10%.
    if new_ch < 0.9 * ch:
        new_ch += divisor
    return new_ch


class ConvBNReLU(nn.Sequential):
    def __init__(self, in_channel, out_channel, kernel_size=3, stride=1, groups=1): #group=1就是普通卷积，如果groups与输入特征矩阵深度相同就是DW卷积
        padding = (kernel_size - 1) // 2
        super(ConvBNReLU, self).__init__(
            nn.Conv2d(in_channel, out_channel, kernel_size, stride, padding, groups=groups, bias=False),
            nn.BatchNorm2d(out_channel),
            nn.ReLU6(inplace=True)
        )


class InvertedResidual(nn.Module):
    def __init__(self, in_channel, out_channel, stride, expand_ratio):
        super(InvertedResidual, self).__init__()
        hidden_channel = in_channel * expand_ratio
        self.use_shortcut = stride == 1 and in_channel == out_channel

        layers = []
        if expand_ratio != 1:
            # 1x1 pointwise conv
            layers.append(ConvBNReLU(in_channel, hidden_channel, kernel_size=1))
        layers.extend([
            # 3x3 depthwise conv
            ConvBNReLU(hidden_channel, hidden_channel, stride=stride, groups=hidden_channel),
            # 1x1 pointwise conv(linear) 线性激活函数y=x，不添加激活函数就是线性激活函数
            nn.Conv2d(hidden_channel, out_channel, kernel_size=1, bias=False),
            nn.BatchNorm2d(out_channel),
        ])

        self.conv = nn.Sequential(*layers)

    def forward(self, x):
        if self.use_shortcut:
            return x + self.conv(x)
        else:
            return self.conv(x)


class MobileNetV2(nn.Module):
    def __init__(self, num_classes=1000, alpha=1.0, round_nearest=8):
        super(MobileNetV2, self).__init__()
        block = InvertedResidual
        input_channel = _make_divisible(32 * alpha, round_nearest)#将卷积核个数调整为round_nearesrt的整数倍，为了更好的调用硬件设备
        last_channel = _make_divisible(1280 * alpha, round_nearest)

        inverted_residual_setting = [
            # t, c, n, s
            [1, 16, 1, 1],
            [6, 24, 2, 2],
            [6, 32, 3, 2],
            [6, 64, 4, 2],
            [6, 96, 3, 1],
            [6, 160, 3, 2],
            [6, 320, 1, 1],
        ]

        features = []
        # conv1 layer
        features.append(ConvBNReLU(3, input_channel, stride=2))
        # building inverted residual residual blockes
        for t, c, n, s in inverted_residual_setting:
            output_channel = _make_divisible(c * alpha, round_nearest)
            for i in range(n):
                stride = s if i == 0 else 1
                features.append(block(input_channel, output_channel, stride, expand_ratio=t))
                input_channel = output_channel
        # building last several layers
        features.append(ConvBNReLU(input_channel, last_channel, 1))
        # combine feature layers
        self.features = nn.Sequential(*features)

        # building classifier
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.classifier = nn.Sequential(
            nn.Dropout(0.2),
            nn.Linear(last_channel, num_classes)
        )

        # weight initialization
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out')
                if m.bias is not None:
                    nn.init.zeros_(m.bias)
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.ones_(m.weight)
                nn.init.zeros_(m.bias)
            elif isinstance(m, nn.Linear):
                nn.init.normal_(m.weight, 0, 0.01)
                nn.init.zeros_(m.bias)

    def forward(self, x):
        x = self.features(x)
        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        x = self.classifier(x)
        return x

• def _make_divisible(ch,divisor=8, min_ch=None): 保证输出是8的整数倍，而且会输出最接近的8的整数倍
• class ConvBNReLU(nn.Sequential): 继承Sequential 然后使用super() 函数调用父类(超类)，使得卷积层，BN层和ReLU6层按序列排放
• hidden_channel 来控制反残差结构中卷积层扩展的比例
• self.use_shortcut = stride ==1 and in_channel = out_channel 只有当stride=1，输入通道和输出通道相同的情况下才会使用shortcut
• if expand_ratio !=1: 当expand_ratio等于1时，反残差结构不会改变输入的通道数，也就不需要使用$1\times 1$的卷积操作对输入矩阵进行深度扩充。

---

train.py

import os
import json

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

from model_v2 import MobileNetV2


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

    batch_size = 16
    epochs = 5

    data_transform = {
        "train": transforms.Compose([transforms.RandomResizedCrop(224),
                                     transforms.RandomHorizontalFlip(),
                                     transforms.ToTensor(),
                                     transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]),
        "val": transforms.Compose([transforms.Resize(256),
                                   transforms.CenterCrop(224),
                                   transforms.ToTensor(),
                                   transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])}

    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)

    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))

    # create model
    net = MobileNetV2(num_classes=5)

    # load pretrain weights
    # download url: https://download.pytorch.org/models/mobilenet_v2-b0353104.pth
    model_weight_path = "./mobilenet_v2.pth"
    assert os.path.exists(model_weight_path), "file {} dose not exist.".format(model_weight_path)
    pre_weights = torch.load(model_weight_path, map_location=device)

    # delete classifier weights
    pre_dict = {k: v for k, v in pre_weights.items() if net.state_dict()[k].numel() == v.numel()}
    missing_keys, unexpected_keys = net.load_state_dict(pre_dict, strict=False)

    # freeze features weights
    for param in net.features.parameters():
        param.requires_grad = False

    net.to(device)

    # define loss function
    loss_function = nn.CrossEntropyLoss()

    # construct an optimizer
    params = [p for p in net.parameters() if p.requires_grad]
    optimizer = optim.Adam(params, lr=0.0001)

    best_acc = 0.0
    save_path = './MobileNetV2.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 = net(images.to(device))
            loss = loss_function(logits, labels.to(device))
            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))
                # loss = loss_function(outputs, test_labels)
                predict_y = torch.max(outputs, dim=1)[1]
                acc += torch.eq(predict_y, val_labels.to(device)).sum().item()

                val_bar.desc = "valid epoch[{}/{}]".format(epoch + 1,
                                                           epochs)
        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()

• pre_dict = {k: v for k, v in pre_weights.items() if net.state_dict()[k].numel() == v.numel()} 在下载的官方预训练参数中，num_classes=1000 而在我们的model中num_classes=5
  • net.state_dict()[k].numel(): 提取model模型中的关键字K代表的层的长度
  • v.numel: 是下载的预训练参数中对应层的长度
  • 在本例中的迁移学习希望只训练最后的全连接层(因为分类数不同)，所以该句进行一般判断，当model和预训练参数中的对应层不同时就是全连接层
• net.features.parameters() 在model中我们将反残差结构放在了features中，我们不希望在后面的训练中对其训练，因此冻结其梯度
• ** params = [p for p in net.parameters() if p.requires_grad]** 因为上述过程将features的梯度冻结，所以这里的params只包括我们想要训练的全连接层

---

predict.py

import os
import json

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

from model_v2 import MobileNetV2


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

    data_transform = transforms.Compose(
        [transforms.Resize(256),
         transforms.CenterCrop(224),
         transforms.ToTensor(),
         transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])

    # 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 = MobileNetV2(num_classes=5).to(device)
    # load model weights
    model_weight_path = "./MobileNetV2.pth"
    model.load_state_dict(torch.load(model_weight_path, map_location=device))
    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()

---

1. https://blog.csdn.net/tintinetmilou/article/details/81607721 ↩︎