ContraCLIP/lib/evaluation/celeba_attributes/celeba_attr_predictor.py

import json
import torch
import torch.nn as nn
import torch.utils.model_zoo as model_zoo


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


def conv1x1(in_planes, out_planes, stride=1):
    """1x1 convolution"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=(1, 1), stride=(stride, stride), 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):
        identity = 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:
            identity = self.downsample(x)

        out += identity
        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 = conv1x1(inplanes, planes)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = conv3x3(planes, planes, stride)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = conv1x1(planes, planes * self.expansion)
        self.bn3 = nn.BatchNorm2d(planes * self.expansion)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        identity = 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:
            identity = self.downsample(x)

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

        return out


class fc_block(nn.Module):
    def __init__(self, inplanes, planes, drop_rate=0.15):
        super(fc_block, self).__init__()
        self.fc = nn.Linear(inplanes, planes)
        self.bn = nn.BatchNorm1d(planes)
        if drop_rate > 0:
            self.dropout = nn.Dropout(drop_rate)
        self.relu = nn.ReLU(inplace=True)
        self.drop_rate = drop_rate

    def forward(self, x):
        x = self.fc(x)
        x = self.bn(x)
        if self.drop_rate > 0:
            x = self.dropout(x)
        x = self.relu(x)
        return x


class ResNet(nn.Module):
    def __init__(self,
                 block,
                 layers,
                 attr_file,
                 zero_init_residual=False,
                 dropout_rate=0):
        super(ResNet, self).__init__()
        self.inplanes = 64
        self.conv1 = nn.Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 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.AdaptiveAvgPool2d((1, 1))
        self.stem = fc_block(512 * block.expansion, 512, dropout_rate)

        # Construct classifier heads according to the number of values of each attribute
        self.attr_file = attr_file
        with open(self.attr_file, 'r') as f:
            attr_f = json.load(f)
        self.attr_info = attr_f['attr_info']
        for idx, (key, val) in enumerate(self.attr_info.items()):
            num_val = int(len(val["value"]))
            setattr(self, 'classifier' + str(key).zfill(2) + val["name"],
                    nn.Sequential(fc_block(512, 256, dropout_rate), nn.Linear(256, num_val)))

        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)

        # Zero-initialize the last BN in each residual branch, so that the residual branch starts with zeros, and each
        # residual block behaves like an identity.
        # This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
        if zero_init_residual:
            for m in self.modules():
                if isinstance(m, Bottleneck):
                    nn.init.constant_(m.bn3.weight, 0)
                elif isinstance(m, BasicBlock):
                    nn.init.constant_(m.bn2.weight, 0)

    def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(conv1x1(self.inplanes, planes * block.expansion, stride),
                                       nn.BatchNorm2d(planes * block.expansion))

        layers = [block(self.inplanes, planes, stride, downsample)]
        self.inplanes = planes * block.expansion
        for _ 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.stem(x)

        predictions = {}
        for idx, (key, val) in enumerate(self.attr_info.items()):
            classifier = getattr(self, 'classifier' + str(key).zfill(2) + val["name"])
            predictions.update({val["name"]: classifier(x)})

        return predictions


def celeba_attr_predictor(attr_file, pretrained='models/pretrained/celeba_attributes/predictor_1024.pth.tar'):
    model = ResNet(Bottleneck, [3, 4, 6, 3], attr_file=attr_file)
    init_pretrained_weights(model, 'https://download.pytorch.org/models/resnet50-19c8e357.pth')
    model.load_state_dict(torch.load(pretrained)['state_dict'], strict=True)
    return model


def init_pretrained_weights(model, model_url):
    """Initialize model with pretrained weights. Layers that don't match with pretrained layers in name or size are kept
    unchanged.
    """
    pretrain_dict = model_zoo.load_url(model_url)
    model_dict = model.state_dict()
    pretrain_dict = {
        k: v
        for k, v in pretrain_dict.items()
        if k in model_dict and model_dict[k].size() == v.size()
    }
    model_dict.update(pretrain_dict)
    model.load_state_dict(model_dict)