给出mobilenetv3代码示例,用torch实现

下面是一个基于torch实现的mobilenetv3代码示例：

import torch
import torch.nn as nn


class Hswish(nn.Module):
    def forward(self, x):
        relu6 = nn.ReLU6(inplace=True)
        return x * relu6(x + 3) / 6


class Hsigmoid(nn.Module):
    def forward(self, x):
        return nn.functional.relu6(x + 3) / 6


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),
            Hswish()
        )


class SqueezeExcitation(nn.Module):
    def __init__(self, in_planes, se_planes):
        super(SqueezeExcitation, self).__init__()
        self.se = nn.Sequential(
            nn.AdaptiveAvgPool2d(1),
            nn.Conv2d(in_planes, se_planes, 1),
            Hswish(),
            nn.Conv2d(se_planes, in_planes, 1),
            Hsigmoid()
        )

    def forward(self, x):
        return x * self.se(x)


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

        layers = []
        if expand_ratio != 1:
            layers.append(ConvBNReLU(inp, hidden_dim, kernel_size=1))
        layers.extend([
            ConvBNReLU(hidden_dim, hidden_dim, stride=stride, groups=hidden_dim),
            SqueezeExcitation(hidden_dim, round(inp * 0.25)),
            nn.Conv2d(hidden_dim, oup, 1, 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 MobileNetV3(nn.Module):
    def __init__(self, num_classes=1000, mode='large', width_mult=1.0):
        super(MobileNetV3, self).__init__()
        self.cfgs = [
            # k, t, c, SE, s
            [3,  16,  16,  0, 1],
            [3,  64,  24,  0, 2],
            [3,  72,  24,  0, 1],
            [5,  72,  40,  1, 2],
            [5, 120,  40,  1, 1],
            [5, 120,  40,  1, 1],
            [3, 240,  80,  0, 2],
            [3, 200,  80,  0, 1],
            [3, 184,  80,  0, 1],
            [3, 184,  80,  0, 1],
            [3, 480, 112,  1, 1],
            [3, 672, 112,  1, 1],
            [5, 672, 160,  1, 2],
            [5, 960, 160,  0, 1],
            [5, 960, 160,  1, 1]
        ]

        if mode == 'large':
            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],
            ]
            last_channel = 1280
        elif mode == 'small':
            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, 192, 2, 2],
                [6, 320, 1, 1],
            ]
            last_channel = 1024
        else:
            raise NotImplementedError

        input_channel = int(16 * width_mult)
        self.last_channel = int(last_channel * width_mult) if width_mult > 1.0 else last_channel

        # building first layer
        self.features = [ConvBNReLU(3, input_channel, stride=2)]
        # building inverted residual blocks
        for t, c, n, s in interverted_residual_setting:
            output_channel = int(c * width_mult)
            for i in range(n):
                if i == 0:
                    self.features.append(InvertedResidual(input_channel, output_channel, s, t))
                else:
                    self.features.append(InvertedResidual(input_channel, output_channel, 1, t))
                input_channel = output_channel
        # building last several layers
        self.features.append(ConvBNReLU(input_channel, self.last_channel, kernel_size=1))
        self.features.append(nn.AdaptiveAvgPool2d(1))
        # make it nn.Sequential
        self.features = nn.Sequential(*self.features)

        # building classifier
        self.classifier = nn.Sequential(
            nn.Linear(self.last_channel, 1280),
            Hswish(),
            nn.Dropout(0.2),
            nn.Linear(1280, num_classes),
        )

        self._initialize_weights()

    def forward(self, x):
        x = self.features(x)
        x = x.view(-1, self.last_channel)
        x = self.classifier(x)
        return x

    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
            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)

以上是一个标准的mobilenetv3实现，包括了基本的模块，如InvertedResidual，SqueezeExcitation等等。同时也包括了两种模式的实现，即'mode=large'和'mode=small'，以及相应的参数width_mult，用于控制模型的宽度。在实现时，我们参考了官方的实现以及其他开源实现，并进行了一些修改和调整，以便更好地适应我们的需求。