pytorch中MobileNetV2分类模型的源码注解

MobileNetV1《MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications》_程大海的博客-CSDN博客

《MobileNetV2: Inverted Residuals and Linear Bottlenecks》_程大海的博客-CSDN博客

《ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices》_程大海的博客-CSDN博客

pytorch中MobileNetV2分类模型的源码注解_程大海的博客-CSDN博客

pytorch卷积操作nn.Conv中的groups参数用法解释_程大海的博客-CSDN博客_pytorch中groups

---

上一篇《pytorch卷积操作nn.Conv中的groups参数用法解释》中简单介绍了MobileNet中使用的深度可分离卷积，以及pytorch中在实现深度可分离卷积时使用的nn.Conv模块的groups参数。本篇通过代码注释的方式解释一下pytorch中MobileNetV2网络的具体实现过程。

from torch import nn
from .utils import load_state_dict_from_url


__all__ = ['MobileNetV2', 'mobilenet_v2']


model_urls = {
    'mobilenet_v2': 'https://download.pytorch.org/models/mobilenet_v2-b0353104.pth',
}


def _make_divisible(v, divisor, min_value=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
    :param v:
    :param divisor:
    :param min_value:
    :return:
    """
    if min_value is None:
        min_value = divisor
    new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
    # Make sure that round down does not go down by more than 10%.
    if new_v < 0.9 * v:
        new_v += divisor
    return new_v


class ConvBNReLU(nn.Sequential):
    """
        深度可分离卷积：
        1、convolution on each input channel
        2、Batch Normalize
        3、Relu6
    """
    def __init__(self, in_planes, out_planes, kernel_size=3, stride=1, groups=1, norm_layer=None):
        padding = (kernel_size - 1) // 2
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        # 深度可分离卷积，卷积的groups等于卷积输入的通道数，实现每个通道单独进行卷积的目的
        super(ConvBNReLU, self).__init__(
            nn.Conv2d(in_planes, out_planes, kernel_size, stride, padding, groups=groups, bias=False),
            norm_layer(out_planes),
            nn.ReLU6(inplace=True)
        )


class InvertedResidual(nn.Module):
    def __init__(self, inp, oup, stride, expand_ratio, norm_layer=None):
        super(InvertedResidual, self).__init__()
        self.stride = stride
        # 有两种卷积stride模式，stride=1和stride=2
        assert stride in [1, 2]

        if norm_layer is None:
            norm_layer = nn.BatchNorm2d

        hidden_dim = int(round(inp * expand_ratio))
        # 当stride=1且输入、输出通道数相等时，使用short-cut残差连接
        # 当stride=2时不使用short-cut残差连接
        self.use_res_connect = self.stride == 1 and inp == oup

        layers = []
        if expand_ratio != 1:
            # pw 使用扩展因子提升通道数
            layers.append(ConvBNReLU(inp, hidden_dim, kernel_size=1, norm_layer=norm_layer))
        layers.extend([
            # dw， 深度可分离卷积，卷积groups等于输入通道数
            ConvBNReLU(hidden_dim, hidden_dim, stride=stride, groups=hidden_dim, norm_layer=norm_layer),
            # pw-linear， 使用1x1卷积降维
            nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
            norm_layer(oup),
        ])
        self.conv = nn.Sequential(*layers)

    def forward(self, x):
        if self.use_res_connect:
            # stride=1且输入输出维度相等，使用残差连接
            return x + self.conv(x)
        else:
            # 不使用残差连接
            return self.conv(x)


class MobileNetV2(nn.Module):
    def __init__(self,
                 num_classes=1000,
                 width_mult=1.0,
                 inverted_residual_setting=None,
                 round_nearest=8,
                 block=None,
                 norm_layer=None):
        """
        MobileNet V2 main class

        Args:
            num_classes (int): Number of classes
            width_mult (float): Width multiplier - adjusts number of channels in each layer by this amount
            inverted_residual_setting: Network structure
            round_nearest (int): Round the number of channels in each layer to be a multiple of this number
            Set to 1 to turn off rounding
            block: Module specifying inverted residual building block for mobilenet
            norm_layer: Module specifying the normalization layer to use

        """
        super(MobileNetV2, self).__init__()

        if block is None:
            block = InvertedResidual

        if norm_layer is None:
            norm_layer = nn.BatchNorm2d

        input_channel = 32
        last_channel = 1280

        if inverted_residual_setting is None:
            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],
            ]

        # only check the first element, assuming user knows t,c,n,s are required
        if len(inverted_residual_setting) == 0 or len(inverted_residual_setting[0]) != 4:
            raise ValueError("inverted_residual_setting should be non-empty "
                             "or a 4-element list, got {}".format(inverted_residual_setting))

        # building first layer
        input_channel = _make_divisible(input_channel * width_mult, round_nearest)
        self.last_channel = _make_divisible(last_channel * max(1.0, width_mult), round_nearest)
        # first 3x3 convolution
        features = [ConvBNReLU(3, input_channel, stride=2, norm_layer=norm_layer)]
        # building inverted residual blocks
        for t, c, n, s in inverted_residual_setting:
            output_channel = _make_divisible(c * width_mult, round_nearest)
            for i in range(n):
                # 在每个反转卷积中，除第一个卷积外其他卷积操作均使用stride=1
                stride = s if i == 0 else 1
                features.append(block(input_channel, output_channel, stride, expand_ratio=t, norm_layer=norm_layer))
                input_channel = output_channel
        # building last several layers, 使用1x1卷积降低通道数
        features.append(ConvBNReLU(input_channel, self.last_channel, kernel_size=1, norm_layer=norm_layer))
        # make it nn.Sequential
        # 底层CNN进行特征提取
        self.features = nn.Sequential(*features)

        # building classifier
        # 构建上层分类器
        self.classifier = nn.Sequential(
            nn.Dropout(0.2),
            nn.Linear(self.last_channel, num_classes),
        )

        # weight initialization
        # 权重参数初始化
        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.GroupNorm)):
                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_impl(self, x):
        # This exists since TorchScript doesn't support inheritance, so the superclass method
        # (this one) needs to have a name other than `forward` that can be accessed in a subclass
        x = self.features(x)
        # Cannot use "squeeze" as batch-size can be 1 => must use reshape with x.shape[0]
        # 通常在卷积网络中，需要把最后一个卷积的结果进行flatten压平，然后使用全连接层，并最终输出与分类类别数一致的输出数量
        # 在MobileNetV2中 在最后一个卷积结果之后使用自适应平均池化，将卷积结果[N, C, H, W]自适应平均池化后得到[N, C, 1, 1],起到
        # 代替全连接层的作用，使得网络可以自动处理任意大小的图片
        # 原始论文中使用的训练数据是224x224，但是我实际使用中使用的是40x40大小，只需要把self.classifier部分的分类器头换掉即可
        x = nn.functional.adaptive_avg_pool2d(x, 1).reshape(x.shape[0], -1)
        x = self.classifier(x)
        return x

    def forward(self, x):
        return self._forward_impl(x)


def mobilenet_v2(pretrained=False, progress=True, **kwargs):
    """
    Constructs a MobileNetV2 architecture from
    `"MobileNetV2: Inverted Residuals and Linear Bottlenecks" <https://arxiv.org/abs/1801.04381>`_.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    model = MobileNetV2(**kwargs)
    if pretrained:
        # 加载在ImageNet上预训练的参数
        state_dict = load_state_dict_from_url(model_urls['mobilenet_v2'],
                                              progress=progress)
        model.load_state_dict(state_dict)
    return model