pytorch复现MobieNetV2


python 复制代码
import torch
import torch.nn as nn


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):
        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_ration):
        super(InvertedResidual, self).__init__()
        hidden_channel = in_channel * expand_ration
        self.use_shortcut = (stride==1 and in_channel==out_channel)

        layers = []

        if expand_ration != 1:
            layers.append(ConvBNReLU(in_channel, hidden_channel, kernel_size=1))

        #extent 添加多个元素
        layers.extend([
            #group=1 就是普通卷积, group=hidden_channel 就是depthwise卷积
            ConvBNReLU(hidden_channel, hidden_channel, stride=stride, groups=hidden_channel),
            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
        #使通道数32*alpha 变成最接近 round_nearest 的整倍数
        input_channel = _make_divisible(32 * alpha, round_nearest)
        last_channel = _make_divisible(1280 * alpha, round_nearest)

        '''
            t:扩展因子
            c:输出特征矩阵深度channel
            n:bottleneck的重复次数
            s:步距
        '''
        inverted_residuals_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))

        for t, c, n, s in inverted_residuals_setting:
            output_channel = _make_divisible(c*alpha, round_nearest)
            for i in range(n):
                #每个n层bottleneck中只有第一层的stride=s, 剩余的层stride=1
                stride = s if i == 0 else 1
                features.append(block(input_channel, output_channel, stride, expand_ration=t))
                input_channel = output_channel

        features.append(ConvBNReLU(input_channel, last_channel, 1))

        self.features = nn.Sequential(*features)

        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
相关推荐
_WndProc3 分钟前
【Python】Flask网页
开发语言·python·flask
笑衬人心。4 分钟前
初学Spring AI 笔记
人工智能·笔记·spring
互联网搬砖老肖5 分钟前
Python 中如何使用 Conda 管理版本和创建 Django 项目
python·django·conda
luofeiju14 分钟前
RGB下的色彩变换:用线性代数解构色彩世界
图像处理·人工智能·opencv·线性代数
测试者家园16 分钟前
基于DeepSeek和crewAI构建测试用例脚本生成器
人工智能·python·测试用例·智能体·智能化测试·crewai
张较瘦_20 分钟前
[论文阅读] 人工智能 + 软件工程 | Call Me Maybe:用图神经网络增强JavaScript调用图构建
论文阅读·人工智能·软件工程
大模型真好玩20 分钟前
准确率飙升!Graph RAG如何利用知识图谱提升RAG答案质量(四)——微软GraphRAG代码实战
人工智能·python·mcp
前端付豪28 分钟前
11、打造自己的 CLI 工具:从命令行到桌面效率神器
后端·python
前端付豪28 分钟前
12、用类写出更可控、更易扩展的爬虫框架🕷
后端·python
Baihai_IDP34 分钟前
vec2text 技术已开源!一定条件下,文本嵌入向量可“近乎完美地”还原
人工智能·面试·llm