模型代码"/>
CenterNet网络模型代码
这里主要针对在CenterNet中表现还可以的改进过的 dla 网络进行分析，主要还是结合代码进行说明。下面就是代码：
# BN 动量参数
BN_MOMENTUM = 0.1
# 获取打印日志对象
logger = logging.getLogger(__name__)
# 获取预训练网络
def get_model_url(data='imagenet', name='dla34', hash='ba72cf86'):return join('', data, '{}-{}.pth'.format(name, hash))
# 3*3 卷积
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)#基础模块（Res18 34中运用）
#3*3 bn relu -> 3*3 bn relu + x(res)
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 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)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 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)self.stride = stridedef forward(self, x, residual=None):if residual is None:residual = xout = self.conv1(x)out = self.bn1(out)out = self.relu(out)out = self.conv2(out)out = self.bn2(out)out += residualout = self.relu(out)return out
# 残差瓶颈层(50以上的层次用)
#Resnet bottleneck
# 这个瓶颈层其实和 ResNet中的瓶颈层类似，只不过其宽度不同，这里更宽
class Bottleneck(nn.Module):expansion = 2#这里的膨胀率是2，也就是让网络更宽# 初始化def __init__(self, inplanes, planes, stride=1, dilation=1):super(Bottleneck, self).__init__()expansion = Bottleneck.expansionbottle_planes = planes // expansionself.conv1 = nn.Conv2d(inplanes, bottle_planes,kernel_size=1, bias=False)self.bn1 = nn.BatchNorm2d(bottle_planes, momentum=BN_MOMENTUM)self.conv2 = nn.Conv2d(bottle_planes, bottle_planes, kernel_size=3,stride=stride, padding=dilation,bias=False, dilation=dilation)self.bn2 = nn.BatchNorm2d(bottle_planes, momentum=BN_MOMENTUM)self.conv3 = nn.Conv2d(bottle_planes, planes,kernel_size=1, bias=False)self.bn3 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)self.relu = nn.ReLU(inplace=True)self.stride = stridedef forward(self, x, residual=None):if residual is None:residual = xout = 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 += residualout = self.relu(out)return out#ResneXt bottleneck
class BottleneckX(nn.Module):expansion = 2cardinality = 32def __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 * cardinalitybottle_planes = planes * cardinality // 32self.conv1 = nn.Conv2d(inplanes, bottle_planes,kernel_size=1, bias=False)self.bn1 = nn.BatchNorm2d(bottle_planes, momentum=BN_MOMENTUM)# 使用了组卷积，划分方式为 32 组，如果输入的通道是128，输出通道是256 则卷积核会变成 32*8*3*3*4，即每次只考虑在输入4 个通道上 做卷积，输出为8 通道，然后再把 32个输出的 8 通道特征融合(concat)为 256维self.conv2 = nn.Conv2d(bottle_planes, bottle_planes, kernel_size=3,stride=stride, padding=dilation, bias=False,dilation=dilation, groups=cardinality)self.bn2 = nn.BatchNorm2d(bottle_planes, momentum=BN_MOMENTUM)self.conv3 = nn.Conv2d(bottle_planes, planes,kernel_size=1, bias=False)self.bn3 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)self.relu = nn.ReLU(inplace=True)self.stride = stridedef forward(self, x, residual=None):if residual is None:residual = xout = 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 += residualout = self.relu(out)return out# 根 1*1 (in*out) 调整维度的卷积操作，可以使用残差模块
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 = nn.BatchNorm2d(out_channels, momentum=BN_MOMENTUM)self.relu = nn.ReLU(inplace=True)self.residual = residualdef forward(self, *x):children = xx = self.conv(torch.cat(x, 1))x = self.bn(x)if self.residual:x += children[0]x = self.relu(x)return x# 3*3 conv stack
class Tree(nn.Module):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_channelsif level_root:root_dim += in_channelsif levels == 1:self.tree1 = block(in_channels, out_channels, stride,dilation=dilation)self.tree2 = block(out_channels, out_channels, 1,dilation=dilation)else:# 堆叠的 BasicBlock 树结构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_rootself.root_dim = root_dimself.downsample = Noneself.project = Noneself.levels = levelsif 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),nn.BatchNorm2d(out_channels, momentum=BN_MOMENTUM))def forward(self, x, residual=None, children=None):children = [] if children is None else children#下采样为True则进行下采样，不然就是 x 本身bottom = self.downsample(x) if self.downsample else x# 是否使用1*1卷积进行维度改变(Cin!=Cout)residual = self.project(bottom) if self.project else bottomif self.level_root:children.append(bottom)x1 = self.tree1(x, residual)# 通过一个残差块if self.levels == 1:x2 = self.tree2(x1)#通过第二个残差块#进行组合x2和x1,进行1*1卷积x = self.root(x2, x1, *children)else:children.append(x1)x = self.tree2(x1, children=children)return x#DLA network backbone
class DLA(nn.Module):def __init__(self, levels, channels, num_classes=1000,block=BasicBlock, residual_root=False, linear_root=False):super(DLA, self).__init__()self.channels = channels#[16,32,64,128,256,512]self.num_classes = num_classes#94# pre-precess 7*7 convself.base_layer = nn.Sequential(nn.Conv2d(3, channels[0], kernel_size=7, stride=1,padding=3, bias=False),nn.BatchNorm2d(channels[0], momentum=BN_MOMENTUM),nn.ReLU(inplace=True))self.level0 = self._make_conv_level(channels[0], channels[0], levels[0])self.level1 = self._make_conv_level(channels[0], channels[1], levels[1], stride=2)self.level2 = Tree(levels[2], block, channels[1], channels[2], 2,level_root=False,root_residual=residual_root)self.level3 = Tree(levels[3], block, channels[2], channels[3], 2,level_root=True, root_residual=residual_root)self.level4 = Tree(levels[4], block, channels[3], channels[4], 2,level_root=True, root_residual=residual_root)self.level5 = Tree(levels[5], block, channels[4], channels[5], 2,level_root=True, root_residual=residual_root)# 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_()# 构建每阶段的卷积def _make_level(self, block, inplanes, planes, blocks, stride=1):downsample = Noneif stride != 1 or inplanes != planes:downsample = nn.Sequential(nn.MaxPool2d(stride, stride=stride),nn.Conv2d(inplanes, planes,kernel_size=1, stride=1, bias=False),nn.BatchNorm2d(planes, momentum=BN_MOMENTUM),)layers = []layers.append(block(inplanes, planes, stride, downsample=downsample))for i in range(1, blocks):layers.append(block(inplanes, planes))return nn.Sequential(*layers)# 3*3 conv def _make_conv_level(self, inplanes, planes, convs, stride=1, dilation=1):modules = []for i in range(convs):modules.extend([nn.Conv2d(inplanes, planes, kernel_size=3,stride=stride if i == 0 else 1,padding=dilation, bias=False, dilation=dilation),nn.BatchNorm2d(planes, momentum=BN_MOMENTUM),nn.ReLU(inplace=True)])inplanes = planesreturn nn.Sequential(*modules)def forward(self, x):y = []x = self.base_layer(x)for i in range(6):x = getattr(self, 'level{}'.format(i))(x)y.append(x)return y#levl0-5 out put# 加载预训练模型def load_pretrained_model(self, data='imagenet', name='dla34', hash='ba72cf86'):# fc = self.fcif name.endswith('.pth'):model_weights = torch.load(data + name)else:model_url = get_model_url(data, name, hash)model_weights = model_zoo.load_url(model_url)num_classes = len(model_weights[list(model_weights.keys())[-1]])self.fc = nn.Conv2d(self.channels[-1], num_classes,kernel_size=1, stride=1, padding=0, bias=True)self.load_state_dict(model_weights)# self.fc = fc# 定义dla的一些模块配置
def dla34(pretrained=True, **kwargs): # DLA-34model = DLA([1, 1, 1, 2, 2, 1],[16, 32, 64, 128, 256, 512],block=BasicBlock, **kwargs)if pretrained:model.load_pretrained_model(data='imagenet', name='dla34', hash='ba72cf86')return model
# 返回自身数据
class Identity(nn.Module):def __init__(self):super(Identity, self).__init__()def forward(self, x):return x# 初始化权重
def fill_fc_weights(layers):for m in layers.modules():if isinstance(m, nn.Conv2d):if m.bias is not None:nn.init.constant_(m.bias, 0)# 初始化权重
def fill_up_weights(up):w = up.weight.dataf = math.ceil(w.size(2) / 2)c = (2 * f - 1 - f % 2) / (2. * f)for i in range(w.size(2)):for j in range(w.size(3)):w[0, 0, i, j] = \(1 - math.fabs(i / f - c)) * (1 - math.fabs(j / f - c))for c in range(1, w.size(0)):w[c, 0, :, :] = w[0, 0, :, :]# 可变形卷积
class DeformConv(nn.Module):def __init__(self, chi, cho):super(DeformConv, self).__init__()self.actf = nn.Sequential(nn.BatchNorm2d(cho, momentum=BN_MOMENTUM),nn.ReLU(inplace=True))self.conv = DCN(chi, cho, kernel_size=(3,3), stride=1, padding=1, dilation=1, deformable_groups=1)def forward(self, x):x = self.conv(x)x = self.actf(x)return x#上采样
class IDAUp(nn.Module):def __init__(self, o, channels, up_f):super(IDAUp, self).__init__()for i in range(1, len(channels)):c = channels[i]f = int(up_f[i]) proj = DeformConv(c, o)#利用可变形卷积进行降维node = DeformConv(o, o)#利用可变形卷积进行调整特征#nn.ConvTranspose2d(in_channels, out_channels, kernel_size, stride=1, padding=0, # output_padding=0, groups=1, bias=True, dilation=1) up = nn.ConvTranspose2d(o, o, f * 2, stride=f, padding=f // 2, output_padding=0,groups=o, bias=False)fill_up_weights(up)setattr(self, 'proj_' + str(i), proj)setattr(self, 'up_' + str(i), up)setattr(self, 'node_' + str(i), node)def forward(self, layers, startp, endp):for i in range(startp + 1, endp):upsample = getattr(self, 'up_' + str(i - startp))project = getattr(self, 'proj_' + str(i - startp))layers[i] = upsample(project(layers[i]))node = getattr(self, 'node_' + str(i - startp))layers[i] = node(layers[i] + layers[i - 1])#upsampling
class DLAUp(nn.Module):def __init__(self, startp, channels, scales, in_channels=None):super(DLAUp, self).__init__()self.startp = startp# 2if in_channels is None:in_channels = channelsself.channels = channels#[64, 128, 256, 512]channels = list(channels)#[64, 128, 256, 512]scales = np.array(scales, dtype=int)#[1,2,4,8]for i in range(len(channels) - 1):#[0,1,2]j = -i - 2#[-2,-3,-4] IDAUp:setattr(self, 'ida_{}'.format(i),IDAUp(channels[j], in_channels[j:],scales[j:] // scales[j]))#set the ida_* 为IDAUp(channels[j], in_channels[j:],scales[j:] // scales[j])scales[j + 1:] = scales[j]in_channels[j + 1:] = [channels[j] for _ in channels[j + 1:]]def forward(self, layers):out = [layers[-1]] # start with 32for i in range(len(layers) - self.startp - 1):ida = getattr(self, 'ida_{}'.format(i))ida(layers, len(layers) -i - 2, len(layers))out.insert(0, layers[-1])return out#线性插值
class Interpolate(nn.Module):def __init__(self, scale, mode):super(Interpolate, self).__init__()self.scale = scaleself.mode = modedef forward(self, x):x = F.interpolate(x, scale_factor=self.scale, mode=self.mode, align_corners=False)return x# 构架全部的 改进 DLA 结构
class DLASeg(nn.Module):def __init__(self, base_name, heads, pretrained, down_ratio, final_kernel,last_level, head_conv, out_channel=0):super(DLASeg, self).__init__()assert down_ratio in [2, 4, 8, 16]# down_ratio=4 defaultself.first_level = int(np.log2(down_ratio)) # first_level=2self.last_level = last_level # deafult 5self.base = globals()[base_name](pretrained=pretrained)#base_name dla34channels = self.base.channels#[16, 32, 64, 128, 256, 512]scales = [2 ** i for i in range(len(channels[self.first_level:]))]#[1,2,4,8]self.dla_up = DLAUp(self.first_level, channels[self.first_level:], scales)if out_channel == 0:out_channel = channels[self.first_level]self.ida_up = IDAUp(out_channel, channels[self.first_level:self.last_level], [2 ** i for i in range(self.last_level - self.first_level)])self.heads = heads#{'hm':94,'reg':2,'wh':2} for head in self.heads:classes = self.heads[head]if head_conv > 0:#head_conv 256#channels[self.first_level]:64# 3*3-->Relu-->1*1fc = nn.Sequential(nn.Conv2d(channels[self.first_level], head_conv,kernel_size=3, padding=1, bias=True),nn.ReLU(inplace=True),nn.Conv2d(head_conv, classes, kernel_size=final_kernel, stride=1, padding=final_kernel // 2, bias=True))if 'hm' in head:fc[-1].bias.data.fill_(-2.19)else:fill_fc_weights(fc)else:fc = nn.Conv2d(channels[self.first_level], classes, kernel_size=final_kernel, stride=1, padding=final_kernel // 2, bias=True)if 'hm' in head:fc.bias.data.fill_(-2.19)else:fill_fc_weights(fc)self.__setattr__(head, fc)def forward(self, x):x = self.base(x)#dla34 outputx = self.dla_up(x)# dla upsamplingy = []for i in range(self.last_level - self.first_level):y.append(x[i].clone())self.ida_up(y, 0, len(y))# [64,128,256] stage2_4 upsample directlyz = {}for head in self.heads:z[head] = self.__getattr__(head)(y[-1])return [z]# 模型主函数
def get_pose_net(num_layers, heads, head_conv=256, down_ratio=4):model = DLASeg('dla{}'.format(num_layers), heads,pretrained=True,down_ratio=down_ratio,final_kernel=1,last_level=5,head_conv=head_conv)return model
代码可能不容易搞懂，因为里面加了递归，网络结构打印信息为,这个为两个堆叠的块结构：
以上是关于CenterNet中用的改进过后的 DLA34的代码，后来会在对该网络结构进行一个细致文章分析
更多推荐
CenterNet网络模型代码
发布评论