deep-person-reid/torchreid/models/resnet.py

from __future__ import absolute_import
from __future__ import division

import torch
from torch import nn
from torch.nn import functional as F
import torchvision
import torch.utils.model_zoo as model_zoo


__all__ = ['resnet50', 'resnet50_fc512']


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 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 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 ResNet(nn.Module):
    """
    Residual network
    
    Reference:
    He et al. Deep Residual Learning for Image Recognition. CVPR 2016.
    """
    def __init__(self, num_classes, loss, block, layers,
                 last_stride=2,
                 fc_dims=None,
                 dropout_p=None,
                 **kwargs):
        self.inplanes = 64
        super(ResNet, self).__init__()
        self.loss = loss
        self.feature_dim = 512 * block.expansion
        
        # backbone network
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=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=last_stride)
        
        self.global_avgpool = nn.AdaptiveAvgPool2d(1)
        self.fc = self._construct_fc_layer(fc_dims, 512 * block.expansion, dropout_p)
        self.classifier = nn.Linear(self.feature_dim, num_classes)

        self._init_params()

    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 _construct_fc_layer(self, fc_dims, input_dim, dropout_p=None):
        """
        Construct fully connected layer

        - fc_dims (list or tuple): dimensions of fc layers, if None,
                                   no fc layers are constructed
        - input_dim (int): input dimension
        - dropout_p (float): dropout probability, if None, dropout is unused
        """
        if fc_dims is None:
            self.feature_dim = input_dim
            return None
        
        assert isinstance(fc_dims, (list, tuple)), 'fc_dims must be either list or tuple, but got {}'.format(type(fc_dims))
        
        layers = []
        for dim in fc_dims:
            layers.append(nn.Linear(input_dim, dim))
            layers.append(nn.BatchNorm1d(dim))
            layers.append(nn.ReLU(inplace=True))
            if dropout_p is not None:
                layers.append(nn.Dropout(p=dropout_p))
            input_dim = dim
        
        self.feature_dim = fc_dims[-1]
        
        return nn.Sequential(*layers)

    def _init_params(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.BatchNorm1d):
                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)
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)

    def featuremaps(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 forward(self, x):
        f = self.featuremaps(x)
        v = self.global_avgpool(f)
        v = v.view(v.size(0), -1)
        
        if self.fc is not None:
            v = self.fc(v)
        
        if not self.training:
            return v
        
        y = self.classifier(v)
        
        if self.loss == {'xent'}:
            return y
        elif self.loss == {'xent', 'htri'}:
            return y, v
        else:
            raise KeyError("Unsupported loss: {}".format(self.loss))


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)
    print('Initialized model with pretrained weights from {}'.format(model_url))


"""
Residual network configurations:
--
resnet18: block=BasicBlock, layers=[2, 2, 2, 2]
resnet34: block=BasicBlock, layers=[3, 4, 6, 3]
resnet50: block=Bottleneck, layers=[3, 4, 6, 3]
resnet101: block=Bottleneck, layers=[3, 4, 23, 3]
resnet152: block=Bottleneck, layers=[3, 8, 36, 3]
"""


def resnet50(num_classes, loss, pretrained='imagenet', **kwargs):
    model = ResNet(
        num_classes=num_classes,
        loss=loss,
        block=Bottleneck,
        layers=[3, 4, 6, 3],
        last_stride=2,
        fc_dims=None,
        dropout_p=None,
        **kwargs
    )
    if pretrained == 'imagenet':
        init_pretrained_weights(model, model_urls['resnet50'])
    return model


def resnet50_fc512(num_classes, loss, pretrained='imagenet', **kwargs):
    model = ResNet(
        num_classes=num_classes,
        loss=loss,
        block=Bottleneck,
        layers=[3, 4, 6, 3],
        last_stride=1,
        fc_dims=[512],
        dropout_p=None,
        **kwargs
    )
    if pretrained == 'imagenet':
        init_pretrained_weights(model, model_urls['resnet50'])
    return model