se_resnext.py

'''
New for ResNeXt:
1. Wider bottleneck
2. Add group for conv2
'''

import torch.nn as nn
import math

__all__ = ['SE_ResNeXt', 'se_resnext_50', 'se_resnext_101', 'se_resnext_152']


class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None, num_group=32):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes*2, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes*2)
        self.conv2 = nn.Conv2d(planes*2, planes*2, kernel_size=3, stride=stride,
                               padding=1, bias=False, groups=num_group)
        self.bn2 = nn.BatchNorm2d(planes*2)
        self.conv3 = nn.Conv2d(planes*2, planes * 4, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * 4)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

        if planes == 64:
            self.globalAvgPool = nn.AvgPool2d(56, stride=1)
        elif planes == 128:
            self.globalAvgPool = nn.AvgPool2d(28, stride=1)
        elif planes == 256:
            self.globalAvgPool = nn.AvgPool2d(14, stride=1)
        elif planes == 512:
            self.globalAvgPool = nn.AvgPool2d(7, stride=1)
        self.fc1 = nn.Linear(in_features=planes * 4, out_features=round(planes / 4))
        self.fc2 = nn.Linear(in_features=round(planes / 4), out_features=planes * 4)
        self.sigmoid = nn.Sigmoid()

    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)

        original_out = out
        out = self.globalAvgPool(out)
        out = out.view(out.size(0), -1)
        out = self.fc1(out)
        out = self.relu(out)
        out = self.fc2(out)
        out = self.sigmoid(out)
        out = out.view(out.size(0), out.size(1), 1, 1)
        out = out * original_out

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

        return out


class SE_ResNeXt(nn.Module):

    def __init__(self, block, layers, num_classes=1000, num_group=32):
        self.inplanes = 64
        super(SE_ResNeXt, self).__init__()
        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], num_group)
        self.layer2 = self._make_layer(block, 128, layers[1], num_group, stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], num_group, stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], num_group, 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):
                m.weight.data.fill_(1)
                m.bias.data.zero_()

    def _make_layer(self, block, planes, blocks, num_group, 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, num_group=num_group))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes, num_group=num_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 = x.view(x.size(0), -1)
        x = self.fc(x)

        return x

def se_resnext_50(**kwargs):
    """Constructs a ResNeXt-50 model.
    """
    model = SE_ResNeXt(Bottleneck, [3, 4, 6, 3], **kwargs)
    return model


def se_resnext_101(**kwargs):
    """Constructs a ResNeXt-101 model.
    """
    model = SE_ResNeXt(Bottleneck, [3, 4, 23, 3], **kwargs)
    return model


def se_resnext_152(**kwargs):
    """Constructs a ResNeXt-152 model.
    """
    model = SE_ResNeXt(Bottleneck, [3, 8, 36, 3], **kwargs)
    return model