Pytorch - torchvison.models 模型结构定义

PyTorch 提供了一些预训练模型,便于网络测试,迁移学习等应用.

1. torchvison.models

torchvision.models

torchvison.models 包括:

1.1. ImageNet 1-crop error rates (224x224)

NetworkTop-1 errorTop-5 error
AlexNet43.4520.91
VGG-1130.9811.37
VGG-1330.0710.75
VGG-1628.419.62
VGG-1927.629.12
VGG-11 with batch normalization29.6210.19
VGG-13 with batch normalization28.459.63
VGG-16 with batch normalization26.638.50
VGG-19 with batch normalization25.768.15
ResNet-1830.2410.92
ResNet-3426.708.58
ResNet-5023.857.13
ResNet-10122.636.44
ResNet-15221.695.94
SqueezeNet 1.041.9019.58
SqueezeNet 1.141.8119.38
Densenet-12125.357.83
Densenet-16924.007.00
Densenet-20122.806.43
Densenet-16122.356.20
Inception v322.556.44

1.2. 网络模型的使用

1.2.1. 基于随机初始化权重参数的模型构建

如:

import torchvision.models as models

resnet18 = models.resnet18()
alexnet = models.alexnet()
vgg16 = models.vgg16()
squeezenet = models.squeezenet1_0()
densenet = models.densenet161()
inception = models.inception_v3()

1.2.2. 基于预训练模型初始化权重参数的模型构建

import torchvision.models as models

resnet18 = models.resnet18(pretrained=True)
alexnet = models.alexnet(pretrained=True)
squeezenet = models.squeezenet1_0(pretrained=True)
vgg16 = models.vgg16(pretrained=True)
densenet = models.densenet161(pretrained=True)
inception = models.inception_v3(pretrained=True)

某些模型在训练和评价阶段,包含不同的操作行为,如 batch normalization. 其切换可以采用 model.train()model.eval().

torchvision 提供的所有预训练模型,需要保证网络输入图像是以相同的归一化方式进行处理的. 如,3-channel RGB 图像的 mini-batches,(3xHxW),其中 H 和 W 最小是 224. 图像像素值的区间范围是 [0, 1],然后采用均值mean = [0.485, 0.456, 0.406] 和方差 std = [0.229, 0.224, 0.225] 进行归一化.

如:

normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                 std=[0.229, 0.224, 0.225])

train_loader = torch.utils.data.DataLoader(
    datasets.ImageFolder(traindir, 
                         transforms.Compose([
                             transforms.RandomSizedCrop(224),
                             transforms.RandomHorizontalFlip(),
                             transforms.ToTensor(),
                             normalize, ])),
    batch_size=args.batch_size, 
    shuffle=True,
    num_workers=args.workers, 
    pin_memory=True)

2. 网络结构定义

2.1. AlexNet

Paper - One weird trick for parallelizing convolutional neural networks - 2014

# AlexNet
torchvision.models.alexnet(pretrained=False, **kwargs)

网络结构定义 - alexnet

# https://pytorch.org/docs/stable/_modules/torchvision/models/alexnet.html#alexnet
import torch.nn as nn
import torch.utils.model_zoo as model_zoo

__all__ = ['AlexNet', 'alexnet']

model_urls = {
    'alexnet': 'https://download.pytorch.org/models/alexnet-owt-4df8aa71.pth',
}


class AlexNet(nn.Module):

    def __init__(self, num_classes=1000):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(64, 192, kernel_size=5, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(192, 384, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(384, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(256, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
        )
        self.classifier = nn.Sequential(
            nn.Dropout(),
            nn.Linear(256 * 6 * 6, 4096),
            nn.ReLU(inplace=True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(inplace=True),
            nn.Linear(4096, num_classes),
        )

    def forward(self, x):
        x = self.features(x)
        x = x.view(x.size(0), 256 * 6 * 6)
        x = self.classifier(x)
        return x


def alexnet(pretrained=False, **kwargs):
    """
    AlexNet model architecture
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = AlexNet(**kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['alexnet']))
    return model

2.2. VGGNet

# vgg11 & vgg11_bn
torchvision.models.vgg11(pretrained=False, **kwargs)
torchvision.models.vgg11_bn(pretrained=False, **kwargs)

# vgg13 & vgg13_bn
torchvision.models.vgg13(pretrained=False, **kwargs)
torchvision.models.vgg13_bn(pretrained=False, **kwargs)

# vgg16 & vgg16_bn
torchvision.models.vgg16(pretrained=False, **kwargs)
torchvision.models.vgg16_bn(pretrained=False, **kwargs)

# vgg19 & vgg19_bn
torchvision.models.vgg19(pretrained=False, **kwargs)
torchvision.models.vgg19_bn(pretrained=False, **kwargs)

网络结构定义 - VGGNet

# https://pytorch.org/docs/stable/_modules/torchvision/models/vgg.html
import torch.nn as nn
import torch.utils.model_zoo as model_zoo
import math


__all__ = [
    'VGG', 'vgg11', 'vgg11_bn', 'vgg13', 'vgg13_bn', 'vgg16', 'vgg16_bn',
    'vgg19_bn', 'vgg19',
]


model_urls = {
    'vgg11': 'https://download.pytorch.org/models/vgg11-bbd30ac9.pth',
    'vgg13': 'https://download.pytorch.org/models/vgg13-c768596a.pth',
    'vgg16': 'https://download.pytorch.org/models/vgg16-397923af.pth',
    'vgg19': 'https://download.pytorch.org/models/vgg19-dcbb9e9d.pth',
    'vgg11_bn': 'https://download.pytorch.org/models/vgg11_bn-6002323d.pth',
    'vgg13_bn': 'https://download.pytorch.org/models/vgg13_bn-abd245e5.pth',
    'vgg16_bn': 'https://download.pytorch.org/models/vgg16_bn-6c64b313.pth',
    'vgg19_bn': 'https://download.pytorch.org/models/vgg19_bn-c79401a0.pth',
}


class VGG(nn.Module):

    def __init__(self, features, num_classes=1000, init_weights=True):
        super(VGG, self).__init__()
        self.features = features
        self.classifier = nn.Sequential(
            nn.Linear(512 * 7 * 7, 4096),
            nn.ReLU(True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(True),
            nn.Dropout(),
            nn.Linear(4096, num_classes),
        )
        if init_weights:
            self._initialize_weights()

    def forward(self, x):
        x = self.features(x)
        x = x.view(x.size(0), -1)
        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):
                m.weight.data.normal_(0, 0.01)
                m.bias.data.zero_()


def make_layers(cfg, batch_norm=False):
    layers = []
    in_channels = 3
    for v in cfg:
        if v == 'M':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        else:
            conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
            if batch_norm:
                layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
            else:
                layers += [conv2d, nn.ReLU(inplace=True)]
            in_channels = v
    return nn.Sequential(*layers)


cfg = {
    'A': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'B': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'D': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
    'E': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],
}


def vgg11(pretrained=False, **kwargs):
    """
    VGG 11-layer model (configuration "A")

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    if pretrained:
        kwargs['init_weights'] = False
    model = VGG(make_layers(cfg['A']), **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['vgg11']))
    return model


def vgg11_bn(pretrained=False, **kwargs):
    """
    VGG 11-layer model (configuration "A") with batch normalization

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    if pretrained:
        kwargs['init_weights'] = False
    model = VGG(make_layers(cfg['A'], batch_norm=True), **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['vgg11_bn']))
    return model


def vgg13(pretrained=False, **kwargs):
    """
    VGG 13-layer model (configuration "B")

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    if pretrained:
        kwargs['init_weights'] = False
    model = VGG(make_layers(cfg['B']), **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['vgg13']))
    return model


def vgg13_bn(pretrained=False, **kwargs):
    """
    VGG 13-layer model (configuration "B") with batch normalization

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    if pretrained:
        kwargs['init_weights'] = False
    model = VGG(make_layers(cfg['B'], batch_norm=True), **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['vgg13_bn']))
    return model


def vgg16(pretrained=False, **kwargs):
    """
    VGG 16-layer model (configuration "D")

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    if pretrained:
        kwargs['init_weights'] = False
    model = VGG(make_layers(cfg['D']), **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['vgg16']))
    return model


def vgg16_bn(pretrained=False, **kwargs):
    """
    VGG 16-layer model (configuration "D") with batch normalization

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    if pretrained:
        kwargs['init_weights'] = False
    model = VGG(make_layers(cfg['D'], batch_norm=True), **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['vgg16_bn']))
    return model


def vgg19(pretrained=False, **kwargs):
    """
    VGG 19-layer model (configuration "E")

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    if pretrained:
        kwargs['init_weights'] = False
    model = VGG(make_layers(cfg['E']), **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['vgg19']))
    return model


def vgg19_bn(pretrained=False, **kwargs):
    """
    VGG 19-layer model (configuration 'E') with batch normalization

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    if pretrained:
        kwargs['init_weights'] = False
    model = VGG(make_layers(cfg['E'], batch_norm=True), **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['vgg19_bn']))
    return model

2.3. ResNet

# resnet18
torchvision.models.resnet18(pretrained=False, **kwargs)

# resnet34
torchvision.models.resnet34(pretrained=False, **kwargs)

# resnet50 
torchvision.models.resnet50(pretrained=False, **kwargs)

# resnet101
torchvision.models.resnet101(pretrained=False, **kwargs)

# resnet152
torchvision.models.resnet152(pretrained=False, **kwargs)

网络结构定义 - ResNet:

# https://pytorch.org/docs/stable/_modules/torchvision/models/resnet.html
import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo

__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
           'resnet152']

model_urls = {
    'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
    'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
    'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
    'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
    'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
}


def conv3x3(in_planes, out_planes, stride=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, 
                     kernel_size=3, stride=stride,
                     padding=1, bias=False)


class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)

        return out


class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, 
                               kernel_size=3, stride=stride,
                               padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * 4)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)
        out = self.relu(out)

        out = self.conv3(out)
        out = self.bn3(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)

        return out


class ResNet(nn.Module):

    def __init__(self, block, layers, num_classes=1000):
        self.inplanes = 64
        super(ResNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
                               bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        self.avgpool = nn.AvgPool2d(7, stride=1)
        self.fc = nn.Linear(512 * block.expansion, num_classes)

        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))
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()

    def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(planes * block.expansion),
            )

        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes))

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)

        return x


def resnet18(pretrained=False, **kwargs):
    """
    Constructs a ResNet-18 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet18']))
    return model


def resnet34(pretrained=False, **kwargs):
    """
    Constructs a ResNet-34 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet34']))
    return model


def resnet50(pretrained=False, **kwargs):
    """
    Constructs a ResNet-50 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet50']))
    return model


def resnet101(pretrained=False, **kwargs):
    """
    Constructs a ResNet-101 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet101']))
    return model


def resnet152(pretrained=False, **kwargs):
    """
    Constructs a ResNet-152 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet152']))
    return model

2.4. SqueezeNet

squeezenet1_0:网络结构来自论文 SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size.

squeezenet1_1:网络结构来自于 official SqueezeNet repo.

squeezenet1_1 相比于 squeezenet1_0 计算量少了 2.4x 倍,参数量也稍微少了一些,但并未牺牲精度.

torchvision.models.squeezenet1_0(pretrained=False, **kwargs)
torchvision.models.squeezenet1_1(pretrained=False, **kwargs)

网络结构定义 - SqueezeNet.

import math
import torch
import torch.nn as nn
import torch.nn.init as init
import torch.utils.model_zoo as model_zoo

__all__ = ['SqueezeNet', 'squeezenet1_0', 'squeezenet1_1']

model_urls = {
    'squeezenet1_0': 'https://download.pytorch.org/models/squeezenet1_0-a815701f.pth',
    'squeezenet1_1': 'https://download.pytorch.org/models/squeezenet1_1-f364aa15.pth',
}


class Fire(nn.Module):

    def __init__(self, inplanes, squeeze_planes,
                 expand1x1_planes, expand3x3_planes):
        super(Fire, self).__init__()
        self.inplanes = inplanes
        self.squeeze = nn.Conv2d(inplanes, squeeze_planes, kernel_size=1)
        self.squeeze_activation = nn.ReLU(inplace=True)
        self.expand1x1 = nn.Conv2d(squeeze_planes, expand1x1_planes,
                                   kernel_size=1)
        self.expand1x1_activation = nn.ReLU(inplace=True)
        self.expand3x3 = nn.Conv2d(squeeze_planes, expand3x3_planes,
                                   kernel_size=3, padding=1)
        self.expand3x3_activation = nn.ReLU(inplace=True)

    def forward(self, x):
        x = self.squeeze_activation(self.squeeze(x))
        return torch.cat([
            self.expand1x1_activation(self.expand1x1(x)),
            self.expand3x3_activation(self.expand3x3(x))
        ], 1)


class SqueezeNet(nn.Module):

    def __init__(self, version=1.0, num_classes=1000):
        super(SqueezeNet, self).__init__()
        if version not in [1.0, 1.1]:
            raise ValueError("Unsupported SqueezeNet version {version}:"
                             "1.0 or 1.1 expected".format(version=version))
        self.num_classes = num_classes
        if version == 1.0:
            self.features = nn.Sequential(
                nn.Conv2d(3, 96, kernel_size=7, stride=2),
                nn.ReLU(inplace=True),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(96, 16, 64, 64),
                Fire(128, 16, 64, 64),
                Fire(128, 32, 128, 128),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(256, 32, 128, 128),
                Fire(256, 48, 192, 192),
                Fire(384, 48, 192, 192),
                Fire(384, 64, 256, 256),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(512, 64, 256, 256),
            )
        else:
            self.features = nn.Sequential(
                nn.Conv2d(3, 64, kernel_size=3, stride=2),
                nn.ReLU(inplace=True),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(64, 16, 64, 64),
                Fire(128, 16, 64, 64),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(128, 32, 128, 128),
                Fire(256, 32, 128, 128),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(256, 48, 192, 192),
                Fire(384, 48, 192, 192),
                Fire(384, 64, 256, 256),
                Fire(512, 64, 256, 256),
            )
        # Final convolution is initialized differently form the rest
        final_conv = nn.Conv2d(512, self.num_classes, kernel_size=1)
        self.classifier = nn.Sequential(
            nn.Dropout(p=0.5),
            final_conv,
            nn.ReLU(inplace=True),
            nn.AvgPool2d(13, stride=1)
        )

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                if m is final_conv:
                    init.normal(m.weight.data, mean=0.0, std=0.01)
                else:
                    init.kaiming_uniform(m.weight.data)
                if m.bias is not None:
                    m.bias.data.zero_()

    def forward(self, x):
        x = self.features(x)
        x = self.classifier(x)
        return x.view(x.size(0), self.num_classes)


def squeezenet1_0(pretrained=False, **kwargs):
    """
    SqueezeNet model architecture
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = SqueezeNet(version=1.0, **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['squeezenet1_0']))
    return model



def squeezenet1_1(pretrained=False, **kwargs):
    """
    SqueezeNet 1.1 model
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = SqueezeNet(version=1.1, **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['squeezenet1_1']))
    return model

2.5. DenseNet

Paper - Densely Connected Convolutional Networks - 2016

# densenet121
torchvision.models.densenet121(pretrained=False, **kwargs)
# densenet169
torchvision.models.densenet169(pretrained=False, **kwargs)
# densenet161
torchvision.models.densenet161(pretrained=False, **kwargs)
# densenet201
torchvision.models.densenet201(pretrained=False, **kwargs)

网络结构定义 - DenseNet:

# https://pytorch.org/docs/stable/_modules/torchvision/models/densenet.html
import re
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.model_zoo as model_zoo
from collections import OrderedDict

__all__ = ['DenseNet', 'densenet121', 'densenet169', 'densenet201', 'densenet161']

model_urls = {
    'densenet121': 'https://download.pytorch.org/models/densenet121-a639ec97.pth',
    'densenet169': 'https://download.pytorch.org/models/densenet169-b2777c0a.pth',
    'densenet201': 'https://download.pytorch.org/models/densenet201-c1103571.pth',
    'densenet161': 'https://download.pytorch.org/models/densenet161-8d451a50.pth',
}


def densenet121(pretrained=False, **kwargs):
    """
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = DenseNet(num_init_features=64, growth_rate=32, block_config=(6, 12, 24, 16),
                     **kwargs)
    if pretrained:
        # '.'s are no longer allowed in module names, but pervious _DenseLayer
        # has keys 'norm.1', 'relu.1', 'conv.1', 'norm.2', 'relu.2', 'conv.2'.
        # They are also in the checkpoints in model_urls. This pattern is used
        # to find such keys.
        pattern = re.compile(
            r'^(.*denselayer\d+\.(?:norm|relu|conv))\.((?:[12])\.(?:weight|bias|running_mean|running_var))$')
        state_dict = model_zoo.load_url(model_urls['densenet121'])
        for key in list(state_dict.keys()):
            res = pattern.match(key)
            if res:
                new_key = res.group(1) + res.group(2)
                state_dict[new_key] = state_dict[key]
                del state_dict[key]
        model.load_state_dict(state_dict)
    return model


def densenet169(pretrained=False, **kwargs):
    """
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = DenseNet(num_init_features=64, growth_rate=32, block_config=(6, 12, 32, 32),
                     **kwargs)
    if pretrained:
        # '.'s are no longer allowed in module names, but pervious _DenseLayer
        # has keys 'norm.1', 'relu.1', 'conv.1', 'norm.2', 'relu.2', 'conv.2'.
        # They are also in the checkpoints in model_urls. This pattern is used
        # to find such keys.
        pattern = re.compile(
            r'^(.*denselayer\d+\.(?:norm|relu|conv))\.((?:[12])\.(?:weight|bias|running_mean|running_var))$')
        state_dict = model_zoo.load_url(model_urls['densenet169'])
        for key in list(state_dict.keys()):
            res = pattern.match(key)
            if res:
                new_key = res.group(1) + res.group(2)
                state_dict[new_key] = state_dict[key]
                del state_dict[key]
        model.load_state_dict(state_dict)
    return model


def densenet201(pretrained=False, **kwargs):
    """
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = DenseNet(num_init_features=64, growth_rate=32, block_config=(6, 12, 48, 32),
                     **kwargs)
    if pretrained:
        # '.'s are no longer allowed in module names, but pervious _DenseLayer
        # has keys 'norm.1', 'relu.1', 'conv.1', 'norm.2', 'relu.2', 'conv.2'.
        # They are also in the checkpoints in model_urls. This pattern is used
        # to find such keys.
        pattern = re.compile(
            r'^(.*denselayer\d+\.(?:norm|relu|conv))\.((?:[12])\.(?:weight|bias|running_mean|running_var))$')
        state_dict = model_zoo.load_url(model_urls['densenet201'])
        for key in list(state_dict.keys()):
            res = pattern.match(key)
            if res:
                new_key = res.group(1) + res.group(2)
                state_dict[new_key] = state_dict[key]
                del state_dict[key]
        model.load_state_dict(state_dict)
    return model


def densenet161(pretrained=False, **kwargs):
    """
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = DenseNet(num_init_features=96, growth_rate=48, block_config=(6, 12, 36, 24),
                     **kwargs)
    if pretrained:
        # '.'s are no longer allowed in module names, but pervious _DenseLayer
        # has keys 'norm.1', 'relu.1', 'conv.1', 'norm.2', 'relu.2', 'conv.2'.
        # They are also in the checkpoints in model_urls. This pattern is used
        # to find such keys.
        pattern = re.compile(
            r'^(.*denselayer\d+\.(?:norm|relu|conv))\.((?:[12])\.(?:weight|bias|running_mean|running_var))$')
        state_dict = model_zoo.load_url(model_urls['densenet161'])
        for key in list(state_dict.keys()):
            res = pattern.match(key)
            if res:
                new_key = res.group(1) + res.group(2)
                state_dict[new_key] = state_dict[key]
                del state_dict[key]
        model.load_state_dict(state_dict)
    return model


class _DenseLayer(nn.Sequential):
    def __init__(self, num_input_features, growth_rate, bn_size, drop_rate):
        super(_DenseLayer, self).__init__()
        self.add_module('norm1', nn.BatchNorm2d(num_input_features)),
        self.add_module('relu1', nn.ReLU(inplace=True)),
        self.add_module('conv1', nn.Conv2d(num_input_features, bn_size *
                        growth_rate, kernel_size=1, stride=1, bias=False)),
        self.add_module('norm2', nn.BatchNorm2d(bn_size * growth_rate)),
        self.add_module('relu2', nn.ReLU(inplace=True)),
        self.add_module('conv2', nn.Conv2d(bn_size * growth_rate, growth_rate,
                        kernel_size=3, stride=1, padding=1, bias=False)),
        self.drop_rate = drop_rate

    def forward(self, x):
        new_features = super(_DenseLayer, self).forward(x)
        if self.drop_rate > 0:
            new_features = F.dropout(new_features, p=self.drop_rate, training=self.training)
        return torch.cat([x, new_features], 1)


class _DenseBlock(nn.Sequential):
    def __init__(self, num_layers, num_input_features, bn_size, growth_rate, drop_rate):
        super(_DenseBlock, self).__init__()
        for i in range(num_layers):
            layer = _DenseLayer(num_input_features + i * growth_rate, growth_rate, bn_size, drop_rate)
            self.add_module('denselayer%d' % (i + 1), layer)


class _Transition(nn.Sequential):
    def __init__(self, num_input_features, num_output_features):
        super(_Transition, self).__init__()
        self.add_module('norm', nn.BatchNorm2d(num_input_features))
        self.add_module('relu', nn.ReLU(inplace=True))
        self.add_module('conv', nn.Conv2d(num_input_features, num_output_features,
                                          kernel_size=1, stride=1, bias=False))
        self.add_module('pool', nn.AvgPool2d(kernel_size=2, stride=2))


class DenseNet(nn.Module):
    """
    Densenet-BC model class.
    Args:
        growth_rate (int) - how many filters to add each layer (`k` in paper)
        block_config (list of 4 ints) - how many layers in each pooling block
        num_init_features (int) - the number of filters to learn in the first convolution layer
        bn_size (int) - multiplicative factor for number of bottle neck layers
          (i.e. bn_size * k features in the bottleneck layer)
        drop_rate (float) - dropout rate after each dense layer
        num_classes (int) - number of classification classes
    """
    def __init__(self, growth_rate=32, block_config=(6, 12, 24, 16),
                 num_init_features=64, bn_size=4, drop_rate=0, num_classes=1000):

        super(DenseNet, self).__init__()

        # First convolution
        self.features = nn.Sequential(OrderedDict([
            ('conv0', nn.Conv2d(3, num_init_features, kernel_size=7, stride=2, padding=3, bias=False)),
            ('norm0', nn.BatchNorm2d(num_init_features)),
            ('relu0', nn.ReLU(inplace=True)),
            ('pool0', nn.MaxPool2d(kernel_size=3, stride=2, padding=1)),
        ]))

        # Each denseblock
        num_features = num_init_features
        for i, num_layers in enumerate(block_config):
            block = _DenseBlock(num_layers=num_layers, num_input_features=num_features,
                                bn_size=bn_size, growth_rate=growth_rate, drop_rate=drop_rate)
            self.features.add_module('denseblock%d' % (i + 1), block)
            num_features = num_features + num_layers * growth_rate
            if i != len(block_config) - 1:
                trans = _Transition(num_input_features=num_features, num_output_features=num_features // 2)
                self.features.add_module('transition%d' % (i + 1), trans)
                num_features = num_features // 2

        # Final batch norm
        self.features.add_module('norm5', nn.BatchNorm2d(num_features))

        # Linear layer
        self.classifier = nn.Linear(num_features, num_classes)

        # Official init from torch repo.
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal(m.weight.data)
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()
            elif isinstance(m, nn.Linear):
                m.bias.data.zero_()

    def forward(self, x):
        features = self.features(x)
        out = F.relu(features, inplace=True)
        out = F.avg_pool2d(out, kernel_size=7, stride=1).view(features.size(0), -1)
        out = self.classifier(out)
        return out

2.6. Inception V3

Paper - Rethinking the Inception Architecture for Computer Vision - 2015

torchvision.models.inception_v3(pretrained=False, **kwargs)

网络结构定义 - Inception V3:

# https://pytorch.org/docs/stable/_modules/torchvision/models/inception.html#inception_v3
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.model_zoo as model_zoo

__all__ = ['Inception3', 'inception_v3']

model_urls = {
    # Inception v3 ported from TensorFlow
    'inception_v3_google': 'https://download.pytorch.org/models/inception_v3_google-1a9a5a14.pth',
}


def inception_v3(pretrained=False, **kwargs):
    """
    Inception v3 model architecture.
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    if pretrained:
        if 'transform_input' not in kwargs:
            kwargs['transform_input'] = True
        model = Inception3(**kwargs)
        model.load_state_dict(model_zoo.load_url(model_urls['inception_v3_google']))
        return model

    return Inception3(**kwargs)


class Inception3(nn.Module):

    def __init__(self, num_classes=1000, aux_logits=True, transform_input=False):
        super(Inception3, self).__init__()
        self.aux_logits = aux_logits
        self.transform_input = transform_input
        self.Conv2d_1a_3x3 = BasicConv2d(3, 32, kernel_size=3, stride=2)
        self.Conv2d_2a_3x3 = BasicConv2d(32, 32, kernel_size=3)
        self.Conv2d_2b_3x3 = BasicConv2d(32, 64, kernel_size=3, padding=1)
        self.Conv2d_3b_1x1 = BasicConv2d(64, 80, kernel_size=1)
        self.Conv2d_4a_3x3 = BasicConv2d(80, 192, kernel_size=3)
        self.Mixed_5b = InceptionA(192, pool_features=32)
        self.Mixed_5c = InceptionA(256, pool_features=64)
        self.Mixed_5d = InceptionA(288, pool_features=64)
        self.Mixed_6a = InceptionB(288)
        self.Mixed_6b = InceptionC(768, channels_7x7=128)
        self.Mixed_6c = InceptionC(768, channels_7x7=160)
        self.Mixed_6d = InceptionC(768, channels_7x7=160)
        self.Mixed_6e = InceptionC(768, channels_7x7=192)
        if aux_logits:
            self.AuxLogits = InceptionAux(768, num_classes)
        self.Mixed_7a = InceptionD(768)
        self.Mixed_7b = InceptionE(1280)
        self.Mixed_7c = InceptionE(2048)
        self.fc = nn.Linear(2048, num_classes)

        for m in self.modules():
            if isinstance(m, nn.Conv2d) or isinstance(m, nn.Linear):
                import scipy.stats as stats
                stddev = m.stddev if hasattr(m, 'stddev') else 0.1
                X = stats.truncnorm(-2, 2, scale=stddev)
                values = torch.Tensor(X.rvs(m.weight.data.numel()))
                values = values.view(m.weight.data.size())
                m.weight.data.copy_(values)
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()

    def forward(self, x):
        if self.transform_input:
            x = x.clone()
            x[:, 0] = x[:, 0] * (0.229 / 0.5) + (0.485 - 0.5) / 0.5
            x[:, 1] = x[:, 1] * (0.224 / 0.5) + (0.456 - 0.5) / 0.5
            x[:, 2] = x[:, 2] * (0.225 / 0.5) + (0.406 - 0.5) / 0.5
        # 299 x 299 x 3
        x = self.Conv2d_1a_3x3(x)
        # 149 x 149 x 32
        x = self.Conv2d_2a_3x3(x)
        # 147 x 147 x 32
        x = self.Conv2d_2b_3x3(x)
        # 147 x 147 x 64
        x = F.max_pool2d(x, kernel_size=3, stride=2)
        # 73 x 73 x 64
        x = self.Conv2d_3b_1x1(x)
        # 73 x 73 x 80
        x = self.Conv2d_4a_3x3(x)
        # 71 x 71 x 192
        x = F.max_pool2d(x, kernel_size=3, stride=2)
        # 35 x 35 x 192
        x = self.Mixed_5b(x)
        # 35 x 35 x 256
        x = self.Mixed_5c(x)
        # 35 x 35 x 288
        x = self.Mixed_5d(x)
        # 35 x 35 x 288
        x = self.Mixed_6a(x)
        # 17 x 17 x 768
        x = self.Mixed_6b(x)
        # 17 x 17 x 768
        x = self.Mixed_6c(x)
        # 17 x 17 x 768
        x = self.Mixed_6d(x)
        # 17 x 17 x 768
        x = self.Mixed_6e(x)
        # 17 x 17 x 768
        if self.training and self.aux_logits:
            aux = self.AuxLogits(x)
        # 17 x 17 x 768
        x = self.Mixed_7a(x)
        # 8 x 8 x 1280
        x = self.Mixed_7b(x)
        # 8 x 8 x 2048
        x = self.Mixed_7c(x)
        # 8 x 8 x 2048
        x = F.avg_pool2d(x, kernel_size=8)
        # 1 x 1 x 2048
        x = F.dropout(x, training=self.training)
        # 1 x 1 x 2048
        x = x.view(x.size(0), -1)
        # 2048
        x = self.fc(x)
        # 1000 (num_classes)
        if self.training and self.aux_logits:
            return x, aux
        return x


class InceptionA(nn.Module):

    def __init__(self, in_channels, pool_features):
        super(InceptionA, self).__init__()
        self.branch1x1 = BasicConv2d(in_channels, 64, kernel_size=1)

        self.branch5x5_1 = BasicConv2d(in_channels, 48, kernel_size=1)
        self.branch5x5_2 = BasicConv2d(48, 64, kernel_size=5, padding=2)

        self.branch3x3dbl_1 = BasicConv2d(in_channels, 64, kernel_size=1)
        self.branch3x3dbl_2 = BasicConv2d(64, 96, kernel_size=3, padding=1)
        self.branch3x3dbl_3 = BasicConv2d(96, 96, kernel_size=3, padding=1)

        self.branch_pool = BasicConv2d(in_channels, pool_features, kernel_size=1)

    def forward(self, x):
        branch1x1 = self.branch1x1(x)

        branch5x5 = self.branch5x5_1(x)
        branch5x5 = self.branch5x5_2(branch5x5)

        branch3x3dbl = self.branch3x3dbl_1(x)
        branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
        branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl)

        branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)

        outputs = [branch1x1, branch5x5, branch3x3dbl, branch_pool]
        return torch.cat(outputs, 1)


class InceptionB(nn.Module):

    def __init__(self, in_channels):
        super(InceptionB, self).__init__()
        self.branch3x3 = BasicConv2d(in_channels, 384, kernel_size=3, stride=2)

        self.branch3x3dbl_1 = BasicConv2d(in_channels, 64, kernel_size=1)
        self.branch3x3dbl_2 = BasicConv2d(64, 96, kernel_size=3, padding=1)
        self.branch3x3dbl_3 = BasicConv2d(96, 96, kernel_size=3, stride=2)

    def forward(self, x):
        branch3x3 = self.branch3x3(x)

        branch3x3dbl = self.branch3x3dbl_1(x)
        branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
        branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl)

        branch_pool = F.max_pool2d(x, kernel_size=3, stride=2)

        outputs = [branch3x3, branch3x3dbl, branch_pool]
        return torch.cat(outputs, 1)


class InceptionC(nn.Module):

    def __init__(self, in_channels, channels_7x7):
        super(InceptionC, self).__init__()
        self.branch1x1 = BasicConv2d(in_channels, 192, kernel_size=1)

        c7 = channels_7x7
        self.branch7x7_1 = BasicConv2d(in_channels, c7, kernel_size=1)
        self.branch7x7_2 = BasicConv2d(c7, c7, kernel_size=(1, 7), padding=(0, 3))
        self.branch7x7_3 = BasicConv2d(c7, 192, kernel_size=(7, 1), padding=(3, 0))

        self.branch7x7dbl_1 = BasicConv2d(in_channels, c7, kernel_size=1)
        self.branch7x7dbl_2 = BasicConv2d(c7, c7, kernel_size=(7, 1), padding=(3, 0))
        self.branch7x7dbl_3 = BasicConv2d(c7, c7, kernel_size=(1, 7), padding=(0, 3))
        self.branch7x7dbl_4 = BasicConv2d(c7, c7, kernel_size=(7, 1), padding=(3, 0))
        self.branch7x7dbl_5 = BasicConv2d(c7, 192, kernel_size=(1, 7), padding=(0, 3))

        self.branch_pool = BasicConv2d(in_channels, 192, kernel_size=1)

    def forward(self, x):
        branch1x1 = self.branch1x1(x)

        branch7x7 = self.branch7x7_1(x)
        branch7x7 = self.branch7x7_2(branch7x7)
        branch7x7 = self.branch7x7_3(branch7x7)

        branch7x7dbl = self.branch7x7dbl_1(x)
        branch7x7dbl = self.branch7x7dbl_2(branch7x7dbl)
        branch7x7dbl = self.branch7x7dbl_3(branch7x7dbl)
        branch7x7dbl = self.branch7x7dbl_4(branch7x7dbl)
        branch7x7dbl = self.branch7x7dbl_5(branch7x7dbl)

        branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)

        outputs = [branch1x1, branch7x7, branch7x7dbl, branch_pool]
        return torch.cat(outputs, 1)


class InceptionD(nn.Module):

    def __init__(self, in_channels):
        super(InceptionD, self).__init__()
        self.branch3x3_1 = BasicConv2d(in_channels, 192, kernel_size=1)
        self.branch3x3_2 = BasicConv2d(192, 320, kernel_size=3, stride=2)

        self.branch7x7x3_1 = BasicConv2d(in_channels, 192, kernel_size=1)
        self.branch7x7x3_2 = BasicConv2d(192, 192, kernel_size=(1, 7), padding=(0, 3))
        self.branch7x7x3_3 = BasicConv2d(192, 192, kernel_size=(7, 1), padding=(3, 0))
        self.branch7x7x3_4 = BasicConv2d(192, 192, kernel_size=3, stride=2)

    def forward(self, x):
        branch3x3 = self.branch3x3_1(x)
        branch3x3 = self.branch3x3_2(branch3x3)

        branch7x7x3 = self.branch7x7x3_1(x)
        branch7x7x3 = self.branch7x7x3_2(branch7x7x3)
        branch7x7x3 = self.branch7x7x3_3(branch7x7x3)
        branch7x7x3 = self.branch7x7x3_4(branch7x7x3)

        branch_pool = F.max_pool2d(x, kernel_size=3, stride=2)
        outputs = [branch3x3, branch7x7x3, branch_pool]
        return torch.cat(outputs, 1)


class InceptionE(nn.Module):

    def __init__(self, in_channels):
        super(InceptionE, self).__init__()
        self.branch1x1 = BasicConv2d(in_channels, 320, kernel_size=1)

        self.branch3x3_1 = BasicConv2d(in_channels, 384, kernel_size=1)
        self.branch3x3_2a = BasicConv2d(384, 384, kernel_size=(1, 3), padding=(0, 1))
        self.branch3x3_2b = BasicConv2d(384, 384, kernel_size=(3, 1), padding=(1, 0))

        self.branch3x3dbl_1 = BasicConv2d(in_channels, 448, kernel_size=1)
        self.branch3x3dbl_2 = BasicConv2d(448, 384, kernel_size=3, padding=1)
        self.branch3x3dbl_3a = BasicConv2d(384, 384, kernel_size=(1, 3), padding=(0, 1))
        self.branch3x3dbl_3b = BasicConv2d(384, 384, kernel_size=(3, 1), padding=(1, 0))

        self.branch_pool = BasicConv2d(in_channels, 192, kernel_size=1)

    def forward(self, x):
        branch1x1 = self.branch1x1(x)

        branch3x3 = self.branch3x3_1(x)
        branch3x3 = [
            self.branch3x3_2a(branch3x3),
            self.branch3x3_2b(branch3x3),
        ]
        branch3x3 = torch.cat(branch3x3, 1)

        branch3x3dbl = self.branch3x3dbl_1(x)
        branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
        branch3x3dbl = [
            self.branch3x3dbl_3a(branch3x3dbl),
            self.branch3x3dbl_3b(branch3x3dbl),
        ]
        branch3x3dbl = torch.cat(branch3x3dbl, 1)

        branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)

        outputs = [branch1x1, branch3x3, branch3x3dbl, branch_pool]
        return torch.cat(outputs, 1)


class InceptionAux(nn.Module):

    def __init__(self, in_channels, num_classes):
        super(InceptionAux, self).__init__()
        self.conv0 = BasicConv2d(in_channels, 128, kernel_size=1)
        self.conv1 = BasicConv2d(128, 768, kernel_size=5)
        self.conv1.stddev = 0.01
        self.fc = nn.Linear(768, num_classes)
        self.fc.stddev = 0.001

    def forward(self, x):
        # 17 x 17 x 768
        x = F.avg_pool2d(x, kernel_size=5, stride=3)
        # 5 x 5 x 768
        x = self.conv0(x)
        # 5 x 5 x 128
        x = self.conv1(x)
        # 1 x 1 x 768
        x = x.view(x.size(0), -1)
        # 768
        x = self.fc(x)
        # 1000
        return x


class BasicConv2d(nn.Module):

    def __init__(self, in_channels, out_channels, **kwargs):
        super(BasicConv2d, self).__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, bias=False, **kwargs)
        self.bn = nn.BatchNorm2d(out_channels, eps=0.001)

    def forward(self, x):
        x = self.conv(x)
        x = self.bn(x)
        return F.relu(x, inplace=True)

Last modification:December 18th, 2018 at 09:16 pm

One comment

  1. Kang—nice

    很实用,持续关注

Leave a Comment