aicheckv2-api/deep_sort/deep/resnet.py

import torch.nn as nn
import torch


class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, in_channel, out_channel, stride=1, downsample=None, **kwargs):
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel, kernel_size=3,
                               stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(out_channel)
        self.relu = nn.ReLU()
        self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel, kernel_size=3,
                               stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channel)
        self.downsample = downsample

    def forward(self, x):
        identity = x
        if self.downsample is not None:
            identity = self.downsample(x)

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

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

        out += identity
        out = self.relu(out)
        return out


class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, in_channel, out_channel, stride=1, downsample=None,
                 groups=1, width_per_group=64):
        super(Bottleneck, self).__init__()
        width = int(out_channel * (width_per_group / 64.)) * groups

        self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=width, kernel_size=1,
                               stride=1, bias=False)
        self.bn1 = nn.BatchNorm2d(width)
        self.conv2 = nn.Conv2d(in_channels=width, out_channels=width, kernel_size=3,
                               stride=stride, padding=1, bias=False, groups=groups)
        self.bn2 = nn.BatchNorm2d(width)
        self.conv3 = nn.Conv2d(in_channels=width, out_channels=out_channel * self.expansion,
                               kernel_size=1, stride=1, bias=False)
        self.bn3 = nn.BatchNorm2d(out_channel * self.expansion)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample

    def forward(self, x):
        identity = x
        if self.downsample is not None:
            identity = self.downsample(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)

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

        return out


class ResNet(nn.Module):

    def __init__(self, block, blocks_num, reid=False, num_classes=1000, groups=1, width_per_group=64):
        super(ResNet, self).__init__()
        self.reid = reid
        self.in_channel = 64

        self.groups = groups
        self.width_per_group = width_per_group

        self.conv1 = nn.Conv2d(3, self.in_channel, kernel_size=7, stride=2,
                               padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(self.in_channel)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layers(block, 64, blocks_num[0])
        self.layer2 = self._make_layers(block, 128, blocks_num[1], stride=2)
        self.layer3 = self._make_layers(block, 256, blocks_num[2], stride=2)
        # self.layer4 = self._make_layers(block, 512, blocks_num[3], stride=1)

        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(256 * block.expansion, num_classes)

        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.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

    def _make_layers(self, block, channel, block_num, stride=1):
        downsample = None
        if stride != 1 or self.in_channel != channel * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.in_channel, channel * block.expansion, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(channel * block.expansion)
            )
        layers = []
        layers.append(block(self.in_channel, channel, downsample=downsample, stride=stride,
                            groups=self.groups, width_per_group=self.width_per_group))
        self.in_channel = channel * block.expansion

        for _ in range(1, block_num):
            layers.append(block(self.in_channel, channel, groups=self.groups, width_per_group=self.width_per_group))

        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 = torch.flatten(x, 1)

        # B x 512
        if self.reid:
            x = x.div(x.norm(p=2, dim=1, keepdim=True))
            return x
        # classifier
        x = self.fc(x)
        return x


def resnet18(num_classes=1000, reid=False):
    # https://download.pytorch.org/models/resnet18-5c106cde.pth
    return ResNet(BasicBlock, [2, 2, 2, 2], num_classes=num_classes, reid=reid)


def resnet34(num_classes=1000, reid=False):
    # https://download.pytorch.org/models/resnet34-333f7ec4.pth
    return ResNet(BasicBlock, [3, 4, 6, 3], num_classes=num_classes, reid=reid)


def resnet50(num_classes=1000, reid=False):
    # https://download.pytorch.org/models/resnet50-19c8e357.pth
    return ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, reid=reid)


def resnext50_32x4d(num_classes=1000, reid=False):
    # https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth
    groups = 32
    width_per_group = 4
    return ResNet(Bottleneck, [3, 4, 6, 3], reid=reid,
                  num_classes=num_classes, groups=groups, width_per_group=width_per_group)


if __name__ == '__main__':
    net = resnet18(reid=True)
    x = torch.randn(4, 3, 128, 64)
    y = net(x)