当前位置:   article > 正文

PicoDet的学习笔记_picodet模型官方文档数学公式

picodet模型官方文档数学公式

学习资源

Paddle官方教程: 《AI快车道PaddleDetection – 课节4: 闪电版目标检测算法PP-PicoDet》
PicoDet增强版官方介绍: 超强目标检测算法矩阵(PicoDet-XS)
PicoDet论文: PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices
关键点视频也需要学习一下;

1 模型介绍

论文阅读笔记:《PicoDet论文译读笔记》
模型类型: Anchor-Free
关于PicoDet的整体描述,我觉得可以参照VFNet论文对这类模型的介绍:

[VFNet Paper]: Another type of anchor-free detectors are similar to anchor-based one-stage methods, but they remove the usage of anchor boxes. Instead, they classify each point on the feature pyramids [25_FPN] into foreground classes or background, and directly predict the distances from the foreground point to the four sides of the ground-truth bounding box, to produce the detection. Popular methods include DenseBox [26_DenseBox], FASF [27_FASF], FoveaBox [15_FoveaBox], FCOS [9_FCOS], and SPAD [28_SPAD].

技术一览表:

名称cfg
参数初始化KaimingNormal
Loss l o s s v f l + 2 ⋅ l o s s g i o u + 0.25 ⋅ l o s s d f l loss_{vfl}+2\cdot loss_{giou} + 0.25\cdot loss_{dfl} lossvfl+2lossgiou+0.25lossdfl

2 损失函数

首先,来看看loss函数的整体公式:
l o s s = l o s s v f l + 2 ⋅ l o s s g i o u + 0.25 ⋅ l o s s d f l loss = loss_{vfl}+2\cdot loss_{giou} + 0.25\cdot loss_{dfl} loss=lossvfl+2lossgiou+0.25lossdfl
其中,
l o s s v f l loss_{vfl} lossvfl:Varifocal Loss。
l o s s g i o u loss_{giou} lossgiou:GIoU Loss。
l o s s d f l loss_{dfl} lossdfl:Distribution Focal Loss。

2.1 Varifocal Loss —— 分类损失

Varifocal Loss是在VarifocalNet[paper]中提出的;
(关于VarifocalNet论文,请参见《【CVPR 2021】VarifocalNet: An IoU-aware Dense Object Detector的译读笔记》
请参考《mmdetection最小复刻版(十六):iou感知VarifocalNet深入分析》

2.2 GIoU Loss —— 回归损失

用来回归边界框的坐标值;

2.3 Distribution Focal Loss —— 分类损失

Distribution Focal Loss出自论文《Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection》
参考资料:

DFLoss代码实现:

我看了一下PaddleDetection的实现跟MMDetection的实现几乎是一样的;

3 训练自定义数据

训练命令:

python tools/train.py -c configs/model/model_coco.yml
  • 1
声明:本文内容由网友自发贡献,不代表【wpsshop博客】立场,版权归原作者所有,本站不承担相应法律责任。如您发现有侵权的内容,请联系我们。转载请注明出处:https://www.wpsshop.cn/w/煮酒与君饮/article/detail/813843
推荐阅读
相关标签
  

闽ICP备14008679号