Pytorch笔记：根据参数动态构造模型结构

前言

在做实验时，经常要比较相似模型的不同结构对性能的影响。通过传递参数的方法可以很方便地构造出不同的模型结构，从而快速完成模型搭建的工作。

方法

这里以构造VGG模型的结构的backbone为例。代码如下：

import torch
import torch.nn as nn

# __all__代表其它代码import此代码时只能使用__all__列表中的模块
__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',
}

model_paths = {
    'vgg16_bn': r'C:\Users\ocean\Downloads\weights\vgg16_bn-6c64b313.pth',
    'vgg16': r'C:\Users\ocean\Downloads\weights\vgg16-397923af.pth',
}

class VGG(nn.Module):
    def __init__(self,features,num_classes=1000,init_weights=True) -> None:
        super().__init__()
        self.features = features
        self.avgpool = nn.AdaptiveAvgPool2d((7,7))          # 自适应平均池化，指定池化后的输出大小为7X7
        self.classifier = nn.Sequential(
            nn.Linear(512*7*7,4096),
            nn.ReLU(True),              # 据说true和false都没有影响https://blog.csdn.net/denao/article/details/115647687
            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 = self.avgpool(x)
        x = torch.flatten(x,1)          # 把第一个维度中的其它维度去掉，把第一个维度中所有元素拿出放在一个维度中
        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')
                if m.bias is not None:
                    nn.init.constant_(m.bias,0)
            elif isinstance(m,nn.BatchNorm2d):
                nn.init.constant_(m.weight,1)
                nn.init.constant_(m.bias,0)
            elif isinstance(m,nn.Linear):
                nn.init.normal_(m.weight,0,0.01)
                nn.init.constant_(m.bias,0)


def make_layers(cfg,batch_norm=False,sync=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)       # 这里的输入通道一开始为3，后面会不断更新
            if batch_norm:
                if sync:
                    print('use sync backbone')
                    layers += [conv2d, nn.SyncBatchNorm(v), nn.ReLU(inplace=True)]
                else:
                    layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
            else:
                layers += [conv2d, nn.ReLU(inplace=True)]
            in_channels = v
    return nn.Sequential(*layers)

cfgs = {
    '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 _vgg(arch,cfg,batch_norm,pretrained,progress,sync=False,**kwargs):
    if pretrained:
        kwargs['init_weights'] = False
    model = VGG(make_layers(cfgs[cfg],batch_norm=batch_norm,sync=sync),**kwargs)
    if pretrained:
        state_dict = torch.load(model_paths[arch])
        model.load_state_dict(state_dict)
    return model

def vgg11(pretrained=False, progress=True, **kwargs):
    r"""VGG 11-layer model (configuration "A") from
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" `_

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _vgg('vgg11', 'A', False, pretrained, progress, **kwargs)


def vgg11_bn(pretrained=False, progress=True, **kwargs):
    r"""VGG 11-layer model (configuration "A") with batch normalization
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" `_

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _vgg('vgg11_bn', 'A', True, pretrained, progress, **kwargs)


def vgg13(pretrained=False, progress=True, **kwargs):
    r"""VGG 13-layer model (configuration "B")
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" `_

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _vgg('vgg13', 'B', False, pretrained, progress, **kwargs)


def vgg13_bn(pretrained=False, progress=True, **kwargs):
    r"""VGG 13-layer model (configuration "B") with batch normalization
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" `_

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _vgg('vgg13_bn', 'B', True, pretrained, progress, **kwargs)


def vgg16(pretrained=False, progress=True, **kwargs):
    r"""VGG 16-layer model (configuration "D")
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" `_

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _vgg('vgg16', 'D', False, pretrained, progress, **kwargs)


def vgg16_bn(pretrained=False, progress=True, sync=False, **kwargs):
    r"""VGG 16-layer model (configuration "D") with batch normalization
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" `_

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _vgg('vgg16_bn', 'D', True, pretrained, progress, sync=sync, **kwargs)


def vgg19(pretrained=False, progress=True, **kwargs):
    r"""VGG 19-layer model (configuration "E")
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" `_

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _vgg('vgg19', 'E', False, pretrained, progress, **kwargs)


def vgg19_bn(pretrained=False, progress=True, **kwargs):
    r"""VGG 19-layer model (configuration 'E') with batch normalization
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" `_

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _vgg('vgg19_bn', 'E', True, pretrained, progress, **kwargs)

注意到代码中有一个make_layer函数，正是这个函数通过传入的不同参数构造出不同的层。它根据传入的模型参数（是一个列表）中的值，构造不同的层放入列表中。最后返回时通过nn.Sequential(*layers)构造出结构。