网络及组件

18 篇文章 12 订阅
7 篇文章 1 订阅

1. 简介

2. FairMOT代码

2.1 FairMOT网络结构

FairMOT:
  detector: CenterNet
  reid: FairMOTEmbeddingHead
  loss: FairMOTLoss
  tracker: JDETracker

CenterNet:
  backbone: DLA
  neck: CenterNetDLAFPN
  head: CenterNetHead
  post_process: CenterNetPostProcess

CenterNetDLAFPN:
  down_ratio: 4
  last_level: 5
  out_channel: 0
  dcn_v2: True
  with_sge: False

CenterNetHead:
  head_planes: 256
  heatmap_weight: 1
  regress_ltrb: True
  size_weight: 0.1
  size_loss: 'L1'
  offset_weight: 1
  iou_weight: 0

FairMOTEmbeddingHead:
  ch_head: 256
  ch_emb: 128

CenterNetPostProcess:
  max_per_img: 500
  down_ratio: 4
  regress_ltrb: True

JDETracker:
  conf_thres: 0.4
  tracked_thresh: 0.4
  metric_type: cosine

2.1 检测器主干网络 (DLA)

  • BasicBlock:一个基本的残差单元 (2次卷积)
  • Root:把输入张量列表按列拼接,行数不变,然后执行Conv和Relu
  • Tree
  • DLA网络组成
         conv_layers   levels                channels
DLA_cfg = {34: ([1, 1, 1, 2, 2, 1], [16, 32, 64, 128, 256, 512])}
层名层数输入通道数输出通道数卷积核
base13167x7, 16, stride 1
level0116163x3, 16, stride 1
level1116323x3, 32, stride 2
level213264tree1: BasicBlock(ResidualBlock) :
1) 3x3, 64, stride 2
2) 3x3, 64, stride 1
tree2: BasicBlock(ResidualBlock) :
1) 3x3, 64, stride 1
2) 3x3, 64, stride 1
1) 源图x下采样
2) 把通道数提升到64作为residual
3) x1=tree1(x,residual)
4) x2=tree2(x1)
5)把x2,x1按列拼接,然后执行conv, add, relu
level3264128tree1:
tree11: BasicBlock(ResidualBlock) :
1) 3x3, 128, stride 2
2) 3x3, 128, stride 1
tree12: BasicBlock(ResidualBlock) :
1) 3x3, 128, stride 1
2) 3x3, 128, stride 1
1) 源图x下采样
2) 把通道数提升到64作为residual
3) x1=tree11(x,residual)
4) x2=tree12(x1)
5)把x2,x1按列拼接,然后执行conv, add, relu
tree2:
tree21: BasicBlock(ResidualBlock) :
1) 3x3, 128, stride 2
2) 3x3, 128, stride 1
tree22: BasicBlock(ResidualBlock) :
1) 3x3, 128, stride 1
2) 3x3, 128, stride 1
1) 源图x下采样
2) 把通道数提升到64作为residual
3) x1=tree21(x,residual)
4) x2=tree22(x1)
5)把x2,x1按列拼接,然后执行conv, add, relu
level42128256
level51256512
  • 0
    点赞
  • 3
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值