resnet.py

import torch
import torch.nn as nn
import math

from wsi.model.layers import CRF


__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
           'resnet152']


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 * 4, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * 4)
        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):

    def __init__(self, block, layers, num_classes=1, num_nodes=1,
                 use_crf=True):
        """Constructs a ResNet model.

        Args:
            num_classes: int, since we are doing binary classification
                (tumor vs normal), num_classes is set to 1 and sigmoid instead
                of softmax is used later
            num_nodes: int, number of nodes/patches within the fully CRF
            use_crf: bool, use the CRF component or not
        """
        self.inplanes = 64
        super(ResNet, 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])
        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)
        self.crf = CRF(num_nodes) if use_crf else None

        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, 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 forward(self, x):
        """
        Args:
            x: 5D tensor with shape of
            [batch_size, grid_size, 3, crop_size, crop_size],
            where grid_size is the number of patches within a grid (e.g. 9 for
            a 3x3 grid); crop_size is 224 by default for ResNet input;

        Returns:
            logits, 2D tensor with shape of [batch_size, grid_size], the logit
            of each patch within the grid being tumor
        """
        batch_size, grid_size, _, crop_size = x.shape[0:4]
        # flatten grid_size dimension and combine it into batch dimension
        x = x.view(-1, 3, crop_size, crop_size)

        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)
        # feats means features, i.e. patch embeddings from ResNet
        feats = x.view(x.size(0), -1)
        logits = self.fc(feats)

        # restore grid_size dimension for CRF
        feats = feats.view((batch_size, grid_size, -1))
        logits = logits.view((batch_size, grid_size, -1))

        if self.crf:
            logits = self.crf(feats, logits)

        logits = torch.squeeze(logits)

        return logits


def resnet18(**kwargs):
    """Constructs a ResNet-18 model.
    """
    model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)

    return model


def resnet34(**kwargs):
    """Constructs a ResNet-34 model.
    """
    model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs)

    return model


def resnet50(**kwargs):
    """Constructs a ResNet-50 model.
    """
    model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)

    return model


def resnet101(**kwargs):
    """Constructs a ResNet-101 model.
    """
    model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)

    return model


def resnet152(**kwargs):
    """Constructs a ResNet-152 model.
    """
    model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)

    return model