2021SC@SDUSC
CenterNet的骨干网络之DLASeg
DLA全称是Deep Layer Aggregation, 于2018年发表于CVPR。被CenterNet, FairMOT等框架所采用,其效果很不错,准确率和模型复杂度平衡的也比较好。
CenterNet中使用的DLASeg是在DLA-34的基础上添加了Deformable Convolution后的分割网络。
Aggretation聚合是目前设计网络结构的常用的一种技术。如何将不同深度,将不同stage、block之间的信息进行融合是本文探索的目标。
目前常见的聚合方式有skip connection, 如ResNet,这种融合方式仅限于块内部,并且融合方式仅限于简单的叠加。
实现
这部分代码复制自CenterNet官方实现,https://github.com/pprp/SimpleCVReproduction/blob/master/CenterNet/nets/dla34.py
首先是三个模块,BasicBlock和Bottleneck和ResNet中的一致,BottleneckX实际上是ResNeXt中的基础模块,也可以作为DLA中的基础模块。DLA34中调用的依然是BasicBlock。
class BasicBlock(nn.Module):
def __init__(self, inplanes, planes, stride=1, dilation=1):
super(BasicBlock, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=3,
stride=stride, padding=dilation,
bias=False, dilation=dilation)
self.bn1 = BatchNorm(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3,
stride=1, padding=dilation,
bias=False, dilation=dilation)
self.bn2 = BatchNorm(planes)
self.stride = stride
def forward(self, x, residual=None):
if residual is None:
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out += residual
out = self.relu(out)
return out
class Bottleneck(nn.Module):
expansion = 2
def __init__(self, inplanes, planes, stride=1, dilation=1):
super(Bottleneck, self).__init__()
expansion = Bottleneck.expansion
bottle_planes = planes // expansion
self.conv1 = nn.Conv2d(inplanes, bottle_planes,
kernel_size=1, bias=False)
self.bn1 = BatchNorm(bottle_planes)
self.conv2 = nn.Conv2d(bottle_planes, bottle_planes, kernel_size=3,
stride=stride, padding=dilation,
bias=False, dilation=dilation)
self.bn2 = BatchNorm(bottle_planes)
self.conv3 = nn.Conv2d(bottle_planes, planes,
kernel_size=1, bias=False)
self.bn3 = BatchNorm(planes)
self.relu = nn.ReLU(inplace=True)
self.stride = stride
def forward(self, x, residual=None):
if residual is None:
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)
out += residual
out = self.relu(out)
return out
class BottleneckX(nn.Module):
expansion = 2
cardinality = 32
def __init__(self, inplanes, planes, stride=1, dilation=1):
super(BottleneckX, self).__init__()
cardinality = BottleneckX.cardinality
# dim = int(math.floor(planes * (BottleneckV5.expansion / 64.0)))
# bottle_planes = dim * cardinality
bottle_planes = planes * cardinality // 32
self.conv1 = nn.Conv2d(inplanes, bottle_planes,
kernel_size=1, bias=False)
self.bn1 = BatchNorm(bottle_planes)
self.conv2 = nn.Conv2d(bottle_planes, bottle_planes, kernel_size=3,
stride=stride, padding=dilation, bias=False,
dilation=dilation, groups=cardinality)
self.bn2 = BatchNorm(bottle_planes)
self.conv3 = nn.Conv2d(bottle_planes, planes,
kernel_size=1, bias=False)
self.bn3 = BatchNorm(planes)
self.relu = nn.ReLU(inplace=True)
self.stride = stride
def forward(self, x, residual=None):
if residual is None:
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)
out += residual
out = self.relu(out)
return out
然后就是Root类
所有的Aggregation Node都是通过调用这个模块完成的,这个绿色结点也是其连接两个树的根,所以形象地称之为Root。下面是代码实现,forward函数中接受的是多个对象,用来聚合多个层的信息。
class Root(nn.Module):
def __init__(self, in_channels, out_channels, kernel_size, residual):
super(Root, self).__init__()
self.conv = nn.Conv2d(
in_channels, out_channels, 1,
stride=1, bias=False, padding=(kernel_size - 1) // 2)
self.bn = BatchNorm(out_channels)
self.relu = nn.ReLU(inplace=True)
self.residual = residual
def forward(self, *x):
# 输入是多个层输出结果
children = x
x = self.conv(torch.cat(x, 1))
x = self.bn(x)
if self.residual:
x += children[0]
x = self.relu(x)
return x
Tree类
Tree类对应图中的HDA模块,是最核心最复杂的地方。其核心就是递归调用的Tree类的构建,以下是代码。
class Tree(nn.Module):
'''
self.level5 = Tree(levels[5], block, channels[4], channels[5], 2,
level_root=True, root_residual=residual_root)
'''
def __init__(self, levels, block, in_channels, out_channels, stride=1,
level_root=False, root_dim=0, root_kernel_size=1,
dilation=1, root_residual=False):
super(Tree, self).__init__()
if root_dim == 0:
root_dim = 2 * out_channels
if level_root:
root_dim += in_channels
if levels == 1:
self.tree1 = block(in_channels, out_channels, stride,
dilation=dilation)
self.tree2 = block(out_channels, out_channels, 1,
dilation=dilation)
else:
self.tree1 = Tree(levels - 1, block, in_channels, out_channels,
stride, root_dim=0,
root_kernel_size=root_kernel_size,
dilation=dilation, root_residual=root_residual)
self.tree2 = Tree(levels - 1, block, out_channels, out_channels,
root_dim=root_dim + out_channels,
root_kernel_size=root_kernel_size,
dilation=dilation, root_residual=root_residual)
if levels == 1:
self.root = Root(root_dim, out_channels, root_kernel_size,
root_residual)
self.level_root = level_root
self.root_dim = root_dim
self.downsample = None
self.project = None
self.levels = levels
if stride > 1:
self.downsample = nn.MaxPool2d(stride, stride=stride)
if in_channels != out_channels:
self.project = nn.Sequential(
nn.Conv2d(in_channels, out_channels,
kernel_size=1, stride=1, bias=False),
BatchNorm(out_channels)
)
def forward(self, x, residual=None, children=None):
children = [] if children is None else children
bottom = self.downsample(x) if self.downsample else x
# project就是映射,如果输入输出通道数不同则将输入通道数映射到输出通道数
residual = self.project(bottom) if self.project else bottom
if self.level_root:
children.append(bottom)
x1 = self.tree1(x, residual)
if self.levels == 1:
x2 = self.tree2(x1)
# root是出口
x = self.root(x2, x1, *children)
else:
children.append(x1)
x = self.tree2(x1, children=children)
return x
这里涉及了两个比较重要的参数level和level root。
这个类有两个重要的成员变量tree1和tree2,是通过递归的方式迭代生成的,迭代层数通过level进行控制的