Source code for common.vision.models.segmentation.deeplabv2
"""
@author: Junguang Jiang
@contact: JiangJunguang1123@outlook.com
"""
import torch.nn as nn
from torchvision.models.utils import load_state_dict_from_url
model_urls = {
'deeplabv2_resnet101': 'https://cloud.tsinghua.edu.cn/f/2d9a7fc43ce34f76803a/?dl=1'
}
affine_par = True
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, dilation=1, downsample=None):
super(Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, stride=stride, bias=False) # change
self.bn1 = nn.BatchNorm2d(planes, affine=affine_par)
for i in self.bn1.parameters():
i.requires_grad = False
padding = dilation
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, # change
padding=padding, bias=False, dilation=dilation)
self.bn2 = nn.BatchNorm2d(planes, affine=affine_par)
for i in self.bn2.parameters():
i.requires_grad = False
self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(planes * 4, affine=affine_par)
for i in self.bn3.parameters():
i.requires_grad = False
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 ASPP_V2(nn.Module):
def __init__(self, inplanes, dilation_series, padding_series, num_classes):
super(ASPP_V2, self).__init__()
self.conv2d_list = nn.ModuleList()
for dilation, padding in zip(dilation_series, padding_series):
self.conv2d_list.append(
nn.Conv2d(inplanes, num_classes, kernel_size=3, stride=1, padding=padding, dilation=dilation,
bias=True))
for m in self.conv2d_list:
m.weight.data.normal_(0, 0.01)
def forward(self, x):
out = self.conv2d_list[0](x)
for i in range(len(self.conv2d_list) - 1):
out += self.conv2d_list[i + 1](x)
return out
class ResNet(nn.Module):
def __init__(self, block, layers):
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, affine=affine_par)
for i in self.bn1.parameters():
i.requires_grad = False
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1, ceil_mode=True) # change
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=1, dilation=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=1, dilation=4)
for m in self.modules():
if isinstance(m, nn.Conv2d):
m.weight.data.normal_(0, 0.01)
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
def _make_layer(self, block, planes, blocks, stride=1, dilation=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion or dilation == 2 or dilation == 4:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * block.expansion,
kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(planes * block.expansion, affine=affine_par))
for i in downsample._modules['1'].parameters():
i.requires_grad = False
layers = []
layers.append(block(self.inplanes, planes, stride, dilation=dilation, downsample=downsample))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes, dilation=dilation))
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)
return x
class Deeplab(nn.Module):
def __init__(self, backbone, classifier, num_classes):
super(Deeplab, self).__init__()
self.backbone = backbone
self.classifier = classifier
self.num_classes = num_classes
def forward(self, x):
x = self.backbone(x)
y = self.classifier(x)
return y
def get_1x_lr_params_NOscale(self):
"""
This generator returns all the parameters of the net except for
the last classification layer. Note that for each batchnorm layer,
requires_grad is set to False in deeplab_resnet.py, therefore this function does not return
any batchnorm parameter
"""
layers = [self.backbone.conv1, self.backbone.bn1,
self.backbone.layer1, self.backbone.layer2, self.backbone.layer3, self.backbone.layer4]
for layer in layers:
for module in layer.modules():
for param in module.parameters():
if param.requires_grad:
yield param
def get_10x_lr_params(self):
"""
This generator returns all the parameters for the last layer of the net,
which does the classification of pixel into classes
"""
for param in self.classifier.parameters():
yield param
def get_parameters(self, lr=1.):
return [
{'params': self.get_1x_lr_params_NOscale(), 'lr': 0.1 * lr},
{'params': self.get_10x_lr_params(), 'lr': lr}
]
[docs]def deeplabv2_resnet101(num_classes=19, pretrained_backbone=True):
"""Constructs a DeepLabV2 model with a ResNet-101 backbone.
Args:
num_classes (int, optional): number of classes. Default: 19
pretrained_backbone (bool, optional): If True, returns a model pre-trained on ImageNet. Default: True.
"""
backbone = ResNet(Bottleneck, [3, 4, 23, 3])
if pretrained_backbone:
# download from Internet
saved_state_dict = load_state_dict_from_url(model_urls['deeplabv2_resnet101'], map_location=lambda storage, loc: storage, file_name="deeplabv2_resnet101.pth")
new_params = backbone.state_dict().copy()
for i in saved_state_dict:
i_parts = i.split('.')
if not i_parts[1] == 'layer5':
new_params['.'.join(i_parts[1:])] = saved_state_dict[i]
backbone.load_state_dict(new_params)
classifier = ASPP_V2(2048, [6, 12, 18, 24], [6, 12, 18, 24], num_classes)
return Deeplab(backbone, classifier, num_classes)
