MobileNetV2论文笔记以及Pytroch实现

MobileNetV2: Inverted Residuals and Linear Bottlenecks论文笔记以及Pytroch实现

这篇文章的切入点有点意思。作者认为使用RELU函数在某些情况下会导致模型获得的特征信息丢失，因此在某些情况下网络不能加RELU而需要添加线性激活函数（要是恒等映射的话就什么都不加）。此外，如果使用shortcut能够减少信息丢失。据此，作者进行了一系列的论证提出了自己的解决方法。感觉这个角度很新，之前一直认为RELU函数是可以用来防止过拟合的，其优点恰好是其可以丢弃负值，类似于dropout操作。故在设计网络的时候也就一股脑在BN层之后添加RELU函数。

本篇文章介绍比较简单，需要读者理解深度可分离卷积的操作步骤。

一、背景介绍

这篇文章主要目的是提出一个轻量化模型，能够支持手机等算力较小的平台使用。

作者提出了Manifold of interest这个名词来论述当特征维度较小时使用RELU函数进行激活会导致信息丢失。这里我引用一下Classification基础实验系列四——MobileNet v2论文笔记与复现对这个名词的解释。

二、Inverted residual block

故为了解决这个问题，最简单的方法就是当特征维度较高时使用RELU。此外，shortcut连接了原始特征，这可以大大降低信息丢失。而反观常见的Residual Block，都是两头宽，中间窄（宽和窄对应的特征维度）。作者一方面为了更好的节约存储空间，另一方面为了更好的使用RELU，提出了Inverted residual block。

网络具体结构如下：

Pytroch代码如下，这里面因为目的是为了设计轻量化网络，故使用了深度可分离卷积。

class InvertedResidual(nn.Module):
    def __init__(self, inp, oup, stride, expand_ratio):
        super(InvertedResidual, self).__init__()
        self.stride = stride
        assert stride in [1, 2]

        hidden_dim = int(inp * expand_ratio)
        self.use_res_connect = self.stride == 1 and inp == oup

        if expand_ratio == 1:
            self.conv = nn.Sequential(
                # dw
                nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False),
                nn.BatchNorm2d(hidden_dim),
                nn.ReLU6(inplace=True),
                # pw-linear
                nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
                nn.BatchNorm2d(oup),
            )
        else:
            self.conv = nn.Sequential(
                # pw
                nn.Conv2d(inp, hidden_dim, 1, 1, 0, bias=False),
                nn.BatchNorm2d(hidden_dim),
                nn.ReLU6(inplace=True),
                # dw
                nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False),
                nn.BatchNorm2d(hidden_dim),
                nn.ReLU6(inplace=True),
                # pw-linear
                nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
                nn.BatchNorm2d(oup),
            )

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

三、网络结构

好了，接下来就是网络的整体结构了。

Pytroch代码如下：

import torch.nn as nn
import math


def conv_bn(inp, oup, stride):
    return nn.Sequential(
        nn.Conv2d(inp, oup, 3, stride, 1, bias=False),
        nn.BatchNorm2d(oup),
        nn.ReLU6(inplace=True)
    )


def conv_1x1_bn(inp, oup):
    return nn.Sequential(
        nn.Conv2d(inp, oup, 1, 1, 0, bias=False),
        nn.BatchNorm2d(oup),
        nn.ReLU6(inplace=True)
    )


def make_divisible(x, divisible_by=8):
    import numpy as np
    return int(np.ceil(x * 1. / divisible_by) * divisible_by)


class InvertedResidual(nn.Module):
    def __init__(self, inp, oup, stride, expand_ratio):
        super(InvertedResidual, self).__init__()
        self.stride = stride
        assert stride in [1, 2]

        hidden_dim = int(inp * expand_ratio)
        self.use_res_connect = self.stride == 1 and inp == oup

        if expand_ratio == 1:
            self.conv = nn.Sequential(
                # dw
                nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False),
                nn.BatchNorm2d(hidden_dim),
                nn.ReLU6(inplace=True),
                # pw-linear
                nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
                nn.BatchNorm2d(oup),
            )
        else:
            self.conv = nn.Sequential(
                # pw
                nn.Conv2d(inp, hidden_dim, 1, 1, 0, bias=False),
                nn.BatchNorm2d(hidden_dim),
                nn.ReLU6(inplace=True),
                # dw
                nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False),
                nn.BatchNorm2d(hidden_dim),
                nn.ReLU6(inplace=True),
                # pw-linear
                nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
                nn.BatchNorm2d(oup),
            )

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


class MobileNetV2(nn.Module):
    def __init__(self, n_class=1000, input_size=224, width_mult=1.):
        super(MobileNetV2, self).__init__()
        block = InvertedResidual
        input_channel = 32
        last_channel = 1280
        interverted_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],
        ]

        # building first layer
        assert input_size % 32 == 0
        # input_channel = make_divisible(input_channel * width_mult)  # first channel is always 32!
        self.last_channel = make_divisible(last_channel * width_mult) if width_mult > 1.0 else last_channel
        self.features = [conv_bn(3, input_channel, 2)]
        # building inverted residual blocks
        for t, c, n, s in interverted_residual_setting:
            output_channel = make_divisible(c * width_mult) if t > 1 else c
            for i in range(n):
                if i == 0:
                    self.features.append(block(input_channel, output_channel, s, expand_ratio=t))
                else:
                    self.features.append(block(input_channel, output_channel, 1, expand_ratio=t))
                input_channel = output_channel
        # building last several layers
        self.features.append(conv_1x1_bn(input_channel, self.last_channel))
        # make it nn.Sequential
        self.features = nn.Sequential(*self.features)

        # building classifier
        self.classifier = nn.Linear(self.last_channel, n_class)

        self._initialize_weights()

    def forward(self, x):
        x = self.features(x)
        x = x.mean(3).mean(2)
        x = self.classifier(x)
        return x

    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(0, math.sqrt(2. / n))
                if m.bias is not None:
                    m.bias.data.zero_()
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()
            elif isinstance(m, nn.Linear):
                n = m.weight.size(1)
                m.weight.data.normal_(0, 0.01)
                m.bias.data.zero_()


def mobilenet_v2(pretrained=True):
    model = MobileNetV2(width_mult=1)

    if pretrained:
        try:
            from torch.hub import load_state_dict_from_url
        except ImportError:
            from torch.utils.model_zoo import load_url as load_state_dict_from_url
        state_dict = load_state_dict_from_url(
            'https://www.dropbox.com/s/47tyzpofuuyyv1b/mobilenetv2_1.0-f2a8633.pth.tar?dl=1', progress=True)
        model.load_state_dict(state_dict)
    return model


if __name__ == '__main__':
    net = mobilenet_v2(True)