training/networks/resnet.py

# -*- coding: utf-8 -*-
"""
Created on 18-5-21 5:26 PM

@author: ronghuaiyang
"""
import torch
import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo
import torch.nn.utils.weight_norm as weight_norm
import torch.nn.functional as F


# __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 AdaIN(nn.Module):
    def __init__(self, eps=1e-5):
        super().__init__()
        self.eps = eps
        # self.l1 = nn.Linear(num_classes, in_channel*4, bias=True) #bias is good :)

    def c_norm(self, x, bs, ch, eps=1e-7):
        # assert isinstance(x, torch.cuda.FloatTensor)
        x_var = x.var(dim=-1) + eps
        x_std = x_var.sqrt().view(bs, ch, 1, 1)
        x_mean = x.mean(dim=-1).view(bs, ch, 1, 1)
        return x_std, x_mean

    def forward(self, x, y):
        assert x.size(0)==y.size(0)
        size = x.size()
        bs, ch = size[:2]
        x_ = x.view(bs, ch, -1)
        y_ = y.reshape(bs, ch, -1)
        x_std, x_mean = self.c_norm(x_, bs, ch, eps=self.eps)
        y_std, y_mean = self.c_norm(y_, bs, ch, eps=self.eps)
        out =   ((x - x_mean.expand(size)) / x_std.expand(size)) \
                * y_std.expand(size) + y_mean.expand(size)
        return out


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 BasicBlock_adain(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock_adain, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.adain1 = AdaIN()
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.adain2 = AdaIN()
        self.downsample = downsample
        self.stride = stride

    def forward(self, feat):  # x is content, c is style
        x, c = feat
        residual = x

        x = self.conv1(x)
        out = self.adain1(x, c)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.adain2(out, c)

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

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

        return (out, c)


class IRBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None, use_se=True):
        super(IRBlock, self).__init__()
        self.bn0 = nn.BatchNorm2d(inplanes)
        self.conv1 = conv3x3(inplanes, inplanes)
        self.bn1 = nn.BatchNorm2d(inplanes)
        self.prelu = nn.PReLU()
        self.conv2 = conv3x3(inplanes, planes, stride)
        self.bn2 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride
        self.use_se = use_se
        if self.use_se:
            self.se = SEBlock(planes)

    def forward(self, x):
        residual = x
        out = self.bn0(x)
        out = self.conv1(out)
        out = self.bn1(out)
        out = self.prelu(out)

        out = self.conv2(out)
        out = self.bn2(out)
        if self.use_se:
            out = self.se(out)

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

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

        return out


class IRBlock_3conv(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None, use_se=True):
        super(IRBlock_3conv, self).__init__()
        self.bn0 = nn.BatchNorm2d(inplanes)
        self.conv1 = conv3x3(inplanes, inplanes)
        self.bn1 = nn.BatchNorm2d(inplanes)
        self.prelu1 = nn.PReLU()
        self.conv2 = conv3x3(inplanes, planes, stride)
        self.bn2 = nn.BatchNorm2d(planes)
        self.prelu2 = nn.PReLU()
        self.conv3 = conv3x3(planes, planes)
        self.bn3 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride
        self.use_se = use_se
        if self.use_se:
            self.se = SEBlock(planes)
        self.prelu = nn.PReLU()

    def forward(self, x):
        residual = x
        out = self.bn0(x)
        out = self.conv1(out)
        out = self.bn1(out)
        out = self.prelu1(out)

        out = self.conv2(out)
        out = self.bn2(out)
        out = self.prelu2(out)

        out = self.conv3(out)
        out = self.bn3(out)
        if self.use_se:
            out = self.se(out)

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

        out += residual
        out = self.prelu(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 * self.expansion, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * self.expansion)
        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 SEBlock(nn.Module):
    def __init__(self, channel, reduction=16):
        super(SEBlock, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Sequential(
            nn.Linear(channel, channel // reduction),
            nn.PReLU(),
            nn.Linear(channel // reduction, channel),
            nn.Sigmoid()
        )

    def forward(self, x):
        b, c, _, _ = x.size()
        y = self.avg_pool(x).view(b, c)
        y = self.fc(y).view(b, c, 1, 1)
        return x * y


class ResNetFace(nn.Module):
    def __init__(self, block, layers, use_se=True, inc=3):
        self.inplanes = 64
        self.use_se = use_se
        super(ResNetFace, self).__init__()
        self.conv1 = nn.Conv2d(inc, 64, kernel_size=3, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.prelu = nn.PReLU()
        self.maxpool = nn.MaxPool2d(kernel_size=2, stride=2)
        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.bn4 = nn.BatchNorm2d(512)
        #self.dropout = nn.Dropout()
        self.fc5 = nn.Linear(512 * 8 * 8, 512)
        #self.bn5 = nn.BatchNorm1d(512)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.xavier_normal_(m.weight)
            elif isinstance(m, nn.BatchNorm2d) or isinstance(m, nn.BatchNorm1d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.xavier_normal_(m.weight)
                nn.init.constant_(m.bias, 0)

    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, use_se=self.use_se))
        self.inplanes = planes
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes, use_se=self.use_se))

        return nn.Sequential(*layers)

    def features(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.prelu(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        x = self.bn4(x)

        return x
    
    def classifier(self, x):
        x = x.view(x.size(0), -1)
        x = self.fc5(x)

        return x

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

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        x = self.bn4(x)
        #x = self.dropout(x)
        x = x.view(x.size(0), -1)
        x = self.fc5(x)
        #x = self.bn5(x)

        return x


class ResNet(nn.Module):

    def __init__(self, block, layers, basedim=32, inc=1):
        self.inplanes = basedim
        super(ResNet, self).__init__()
        # self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
        #                        bias=False)
        self.conv1 = nn.Conv2d(inc, self.inplanes, kernel_size=3, stride=1, padding=1,
                               bias=False)
        self.bn1 = nn.BatchNorm2d(self.inplanes)
        self.relu = nn.ReLU(inplace=True)
        # self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, basedim, layers[0], stride=2)
        self.layer2 = self._make_layer(block, 2*basedim, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 4*basedim, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 8*basedim, layers[3], stride=2)
        # self.avgpool = nn.AvgPool2d(8, stride=1)
        # self.fc = nn.Linear(512 * block.expansion, num_classes)
        self.fc5 = nn.Linear(512 * 8 * 8, 512)

        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_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 features(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)

        return x
    
    def classifier(self, x):
        x = x.view(x.size(0), -1)
        x = self.fc5(x)

        return x

    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 = nn.AvgPool2d(kernel_size=x.size()[2:])(x)
        # x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc5(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


def resnet_face18(use_se=True, **kwargs):
    model = ResNetFace(IRBlock, [2, 2, 2, 2], use_se=use_se, **kwargs)
    return model


def resnet_face62(use_se=True, **kwargs):
    model = ResNetFace(IRBlock_3conv, [3, 4, 10, 3], use_se=use_se, **kwargs)
    return model

if __name__ == "__main__":
    net = HR_resnet()
    dummy = torch.rand(10,3,256,256)
    x = net(dummy)
    print('output:', x.size())