deeplabv3.py

from collections import OrderedDict

import torch
from torch import nn
from torch.nn import functional as F


class _SimpleSegmentationModel(nn.Module):
    def __init__(self, backbone, classifier, aux_classifier=None):
        super(_SimpleSegmentationModel, self).__init__()
        self.backbone = backbone
        self.classifier = classifier
        self.aux_classifier = aux_classifier

    def forward(self, x):
        input_shape = x.shape[-2:]
        # contract: features is a dict of tensors
        features = self.backbone(x)

        result = OrderedDict()
        x = features["out"]
        x = self.classifier(x)
        x = F.interpolate(x, size=input_shape, mode='bilinear', align_corners=False)
        result["out"] = x

        if self.aux_classifier is not None:
            x = features["aux"]
            x = self.aux_classifier(x)
            x = F.interpolate(x, size=input_shape, mode='bilinear', align_corners=False)
            result["aux"] = x

        return result


class FCN(_SimpleSegmentationModel):
    pass


class DeepLabV3(_SimpleSegmentationModel):
    pass


class FCNHead(nn.Sequential):
    def __init__(self, in_channels, channels):
        inter_channels = in_channels // 4
        layers = [
            nn.Conv2d(in_channels, inter_channels, 3, padding=1, bias=False),
            nn.BatchNorm2d(inter_channels),
            nn.ReLU(),
            nn.Dropout(0.1),
            nn.Conv2d(inter_channels, channels, 1)
        ]

        super(FCNHead, self).__init__(*layers)
        """
        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.GroupNorm)):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
        """


class DeepLabHead(nn.Sequential):
    def __init__(self, in_channels, num_classes):
        super(DeepLabHead, self).__init__(
            ASPP(in_channels, [12, 24, 36]),
            nn.Conv2d(256, 256, 3, padding=1, bias=False),
            nn.BatchNorm2d(256),
            nn.ReLU(),
            nn.Conv2d(256, num_classes, 1)
        )
        """
        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.GroupNorm)):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
        """


class ASPPConv(nn.Sequential):
    def __init__(self, in_channels, out_channels, dilation):
        modules = [
            nn.Conv2d(in_channels, out_channels, 3, padding=dilation, dilation=dilation, bias=False),
            nn.BatchNorm2d(out_channels),
            nn.ReLU()
        ]
        super(ASPPConv, self).__init__(*modules)


class ASPPPooling(nn.Sequential):
    def __init__(self, in_channels, out_channels):
        super(ASPPPooling, self).__init__(
            nn.AdaptiveAvgPool2d(1),
            nn.Conv2d(in_channels, out_channels, 1, bias=False),
            nn.BatchNorm2d(out_channels),
            nn.ReLU())

    def forward(self, x):
        size = x.shape[-2:]
        x = super(ASPPPooling, self).forward(x)
        return F.interpolate(x, size=size, mode='bilinear', align_corners=False)


class ASPP(nn.Module):
    def __init__(self, in_channels, atrous_rates):
        super(ASPP, self).__init__()
        out_channels = 256
        modules = []
        modules.append(nn.Sequential(
            nn.Conv2d(in_channels, out_channels, 1, bias=False),
            nn.BatchNorm2d(out_channels),
            nn.ReLU()))

        rate1, rate2, rate3 = tuple(atrous_rates)
        modules.append(ASPPConv(in_channels, out_channels, rate1))
        modules.append(ASPPConv(in_channels, out_channels, rate2))
        modules.append(ASPPConv(in_channels, out_channels, rate3))
        modules.append(ASPPPooling(in_channels, out_channels))

        self.convs = nn.ModuleList(modules)

        self.project = nn.Sequential(
            nn.Conv2d(5 * out_channels, out_channels, 1, bias=False),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(),
            nn.Dropout(0.5))

    def forward(self, x):
        res = []
        for conv in self.convs:
            res.append(conv(x))
        res = torch.cat(res, dim=1)
        return self.project(res)