resnet_rn.py

import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo
from option import args
import torch
from torch.nn.parameter import Parameter
from torch.autograd import Variable
import torch.nn.functional as F
from reciprocal_norm import RN1d, RN2d

__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)

def init_weights(m):
    classname = m.__class__.__name__
    if classname.find('Conv2d') != -1 or classname.find('ConvTranspose2d') != -1:
        nn.init.kaiming_uniform_(m.weight)
        nn.init.zeros_(m.bias)
    elif classname.find('BatchNorm') != -1:
        nn.init.normal_(m.weight, 1.0, 0.02)
        nn.init.zeros_(m.bias)
    elif classname.find('Linear') != -1:
        nn.init.xavier_normal_(m.weight)
        nn.init.zeros_(m.bias)


def init_weights_c(m):
    if isinstance(m, nn.Conv2d):
        nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
    elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
        nn.init.constant_(m.weight, 1)
        nn.init.constant_(m.bias, 0)


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 = RN2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = RN2d(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 = RN2d(planes) ## replace
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
                               padding=1, bias=False)
        self.bn2 = RN2d(planes) ## replace
        self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
        self.bn3 = RN2d(planes * 4) ## replace
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x  # 0: [36,64,56,56]

        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):

    def __init__(self, block, layers, num_classes=1000):
        self.inplanes = 64
        super(ResNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
                               bias=False)

        self.bn1 = RN2d(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.AvgPool2d(7, stride=1)
        self.fc = nn.Linear(512 * block.expansion, num_classes)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(0, math.sqrt(2. / n))
            elif isinstance(m, nn.BatchNorm2d) or isinstance(m, RN2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()

    def _make_layer(self, block, planes, blocks, stride=1,double=False):
        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),
                RN2d(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 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.fc(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']), strict=False)
        model_dict = model.state_dict()
    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:
        print('resnet101')
        model.load_state_dict(model_zoo.load_url(model_urls['resnet101']), strict=False)
    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 _update_initial_weights_mtn(state_dict, num_classes=1000, num_domains=2, dsbn_type='all'):
    new_state_dict = state_dict.copy()

    for key, val in state_dict.items():
        update_dict = False
        if (('bn' in key or 'downsample.1' in key) and norm_type == 'mtn'):
            update_dict = True

        if (update_dict):
            if 'gate' in key:
                print(key)
                # for d in range(num_domains):
                new_state_dict[key[0:-6] + 'bn.{}.weight'.format('lamda')] = torch.tensor([0.1], dtype=torch.long)

            # elif 'bias' in key:
            #     for d in range(num_domains):
            #         new_state_dict[key[0:-4] + 'bns.{}.bias'.format(d)] = val.data.clone()

            # if 'running_mean' in key:
            #     for d in range(num_domains):
            #         new_state_dict[key[0:-12] + 'bns.{}.running_mean'.format(d)] = val.data.clone()

            # if 'running_var' in key:
            #     for d in range(num_domains):
            #         new_state_dict[key[0:-11] + 'bns.{}.running_var'.format(d)] = val.data.clone()

            # if 'num_batches_tracked' in key:
            #     for d in range(num_domains):
            #         new_state_dict[
            #             key[0:-len('num_batches_tracked')] + 'bns.{}.num_batches_tracked'.format(d)] = val.data.clone()

    if num_classes != 1000 or len([key for key in new_state_dict.keys() if 'fc' in key]) > 1:
        key_list = list(new_state_dict.keys())
        for key in key_list:
            if 'fc' in key:
                print('pretrained {} are not used as initial params.'.format(key))
                del new_state_dict[key]

    return new_state_dict