models/backbone.py

import torch
import torch.nn as nn


def conv3x3(in_planes, out_planes, stride=1):

    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, eps=1e-05)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(planes, eps=1e-05)
        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 ResNet18(nn.Module):

    def __init__(self, nb_feat=384):

        self.inplanes = nb_feat // 4
        super(ResNet18, self).__init__()
        self.conv1 = nn.Conv2d(
            1, nb_feat // 4, kernel_size=3, stride=(2, 1), padding=1, bias=False
        )
        self.bn1 = nn.BatchNorm2d(nb_feat // 4, eps=1e-05)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool1 = nn.MaxPool2d(kernel_size=3, stride=(2, 1), padding=1)
        self.maxpool2 = nn.MaxPool2d(kernel_size=3, stride=(1, 1), padding=1)
        self.layer1 = self._make_layer(BasicBlock, nb_feat // 4, 2, stride=(2, 2))
        self.layer2 = self._make_layer(BasicBlock, nb_feat // 2, 2, stride=2)
        self.layer3 = self._make_layer(BasicBlock, nb_feat, 2, stride=2)

    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, eps=1e-05),
            )

        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, 1, None))

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool1(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.maxpool2(x)

        return x
    
class VGG11(nn.Module):

    def __init__(self, hidden=384):
        super(VGG11, self).__init__()

        self.features = nn.Sequential(

            nn.Conv2d(1,64,3,1,1),
            nn.BatchNorm2d(64),
            nn.ReLU(True),
            nn.MaxPool2d(2,2),

            nn.Conv2d(64,128,3,1,1),
            nn.BatchNorm2d(128),
            nn.ReLU(True),
            nn.MaxPool2d(2,2),

            nn.Conv2d(128,256,3,1,1),
            nn.BatchNorm2d(256),
            nn.ReLU(True),

            nn.Conv2d(256,256,3,1,1),
            nn.BatchNorm2d(256),
            nn.ReLU(True),
            nn.MaxPool2d((2,1),(2,1)),

            nn.Conv2d(256,512,3,1,1),
            nn.BatchNorm2d(512),
            nn.ReLU(True),

            nn.Conv2d(512,512,3,1,1),
            nn.BatchNorm2d(512),
            nn.ReLU(True),
            nn.MaxPool2d((2,1),(2,1)),

            nn.Conv2d(512,hidden,2,1,0),
            nn.BatchNorm2d(hidden),
            nn.ReLU(True),
        )

    def forward(self,x):
        return self.features(x)


class VGG19(nn.Module):

    def __init__(self, hidden=384):
        super(VGG19, self).__init__()

        self.features = nn.Sequential(

            nn.Conv2d(1,64,3,1,1),
            nn.BatchNorm2d(64),
            nn.ReLU(True),

            nn.Conv2d(64,64,3,1,1),
            nn.BatchNorm2d(64),
            nn.ReLU(True),
            nn.MaxPool2d(2,2),

            nn.Conv2d(64,128,3,1,1),
            nn.BatchNorm2d(128),
            nn.ReLU(True),

            nn.Conv2d(128,128,3,1,1),
            nn.BatchNorm2d(128),
            nn.ReLU(True),
            nn.MaxPool2d(2,2),

            nn.Conv2d(128,256,3,1,1),
            nn.BatchNorm2d(256),
            nn.ReLU(True),

            nn.Conv2d(256,256,3,1,1),
            nn.BatchNorm2d(256),
            nn.ReLU(True),

            nn.Conv2d(256,256,3,1,1),
            nn.BatchNorm2d(256),
            nn.ReLU(True),

            nn.Conv2d(256,256,3,1,1),
            nn.BatchNorm2d(256),
            nn.ReLU(True),
            nn.MaxPool2d((2,1),(2,1)),

            nn.Conv2d(256,512,3,1,1),
            nn.BatchNorm2d(512),
            nn.ReLU(True),

            nn.Conv2d(512,512,3,1,1),
            nn.BatchNorm2d(512),
            nn.ReLU(True),

            nn.Conv2d(512,512,3,1,1),
            nn.BatchNorm2d(512),
            nn.ReLU(True),

            nn.Conv2d(512,512,3,1,1),
            nn.BatchNorm2d(512),
            nn.ReLU(True),
            nn.MaxPool2d((2,1),(2,1)),

            nn.Conv2d(512,hidden,2,1,0),
            nn.BatchNorm2d(hidden),
            nn.ReLU(True),
        )

    def forward(self,x):
        return self.features(x)