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
import torch
from torch import nn
from torch.nn import functional as F
__all__ = ["DeepLabV3"]
class DeepLabV3(_SimpleSegmentationModel):
"""
Implements DeepLabV3 model from
`"Rethinking Atrous Convolution for Semantic Image Segmentation"
<https://arxiv.org/abs/1706.05587>`_.
Arguments:
backbone (nn.Module): the network used to compute the features for the model.
The backbone should return an OrderedDict[Tensor], with the key being
"out" for the last feature map used, and "aux" if an auxiliary classifier
is used.
classifier (nn.Module): module that takes the "out" element returned from
the backbone and returns a dense prediction.
aux_classifier (nn.Module, optional): auxiliary classifier used during training
"""
pass
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)
)
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:]
# print(size)
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)