mobilenetv4代码

### MobilenetV4 的代码实现

#### 定义网络结构
为了定义 MobileNetV4 的架构，通常会遵循官方发布的配置文件来构建卷积层和其他组件。下面是一个简化版的 `MobileNetV4` 实现示例：

import torch.nn as nn


class ConvBNReLU(nn.Sequential):
    def __init__(self, in_planes, out_planes, kernel_size=3, stride=1, groups=1):
        padding = (kernel_size - 1) // 2
        super(ConvBNReLU, self).__init__(
            nn.Conv2d(in_planes, out_planes, kernel_size, stride, padding, groups=groups, bias=False),
            nn.BatchNorm2d(out_planes),
            nn.ReLU(inplace=True)
        )


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
    """
    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 InvertedResidual(nn.Module):
    def __init__(self, inp, oup, stride, expand_ratio):
        super(InvertedResidual, self).__init__()
        hidden_dim = int(round(inp * expand_ratio))
        self.use_res_connect = stride == 1 and inp == oup

        layers = []
        if expand_ratio != 1:
            # pw
            layers.append(ConvBNReLU(inp, hidden_dim, kernel_size=1))
        layers.extend([
            # dw
            ConvBNReLU(hidden_dim, hidden_dim, stride=stride, groups=hidden_dim),
            # pw-linear
            nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
            nn.BatchNorm2d(oup),
        ])
        self.conv = nn.Sequential(*layers)

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


class MobileNetV4(nn.Module):
    def __init__(self, num_classes=1000, width_mult=1.0):
        super(MobileNetV4, self).__init__()

        block = InvertedResidual
        input_channel = _make_divisible(32 * width_mult, 8)
        last_channel = _make_divisible(1280 * width_mult, 8) if width_mult > 1.0 else 1280
        
        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 = [ConvBNReLU(3, input_channel, stride=2)]
        
        for t, c, n, s in inverted_residual_setting:
            output_channel = _make_divisible(c * width_mult, 8)
            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
                
        features.append(ConvBNReLU(input_channel, last_channel, kernel_size=1))

        self.features = nn.Sequential(*features)
        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 = x.mean([2, 3])  # global average pooling
        x = self.classifier(x)
        return x

此段代码展示了如何创建一个基于倒残差模块（Inverted Residual Block）的基础版本 MobileNetV4 架构[^1]。