implus/GFocalV2

Issues

• ImportError: cannot import name 'force_fp32' from 'mmcv.runner'

  #19 opened 3 years ago by Lixia1221
  4

• Where does the quality_focal_loss function in gfocal_loss.py call the weight_reduce_loss function ?

  #42 opened 2 months ago by PanffeeReal
  0

• 如何才能从mmdet里拿出来啊，看源码嵌套的太深了 &_&

  #41 opened 3 months ago by Dingerscat
  0

• 关于训练

  #5 opened 4 years ago by liushuai839
  7

• 用于跟踪上精度很低

  #28 opened 3 years ago by Giveupfree
  2

• 关于anchor free+GFocalV2的疑问？

  #9 opened 3 years ago by sunzhe09
  3

• questions about quality_focal_loss

  #40 opened a year ago by lalalafloat
  0

• Welcome update to OpenMMLab 2.0

  #39 opened a year ago by vansin
  0

• how to calcuate the Pearson Correlation Coefficient metric

  #38 opened a year ago by satuoqaq
  0

• The software version used when speeding test

  #37 opened 2 years ago by slacklife
  0

• KeyError: 'GFocalHead is not in the head registry'

  #16 opened 3 years ago by xiaosa96
  7

• Can GFocalV2 applied to softmax classifier?

  #36 opened 2 years ago by Icecream-blue-sky
  0

• GIoULoss in GFL?

  #35 opened 2 years ago by iumyx2612
  0

• TTFNet上部署GFocalV2的一些困惑

  #31 opened 2 years ago
  5

• GFocal

  #34 opened 2 years ago by ChinaRush
  0

• Question about correlation between real localization quality and top-1 generated distribution at training time

  #17 opened 3 years ago by pjh4993
  4

• 获得bbox分布的可视化图的方法

  #33 opened 3 years ago by jackhu-bme
  2

• training custom dataset

  #30 opened 3 years ago by jackhu-bme
  2

• regression_target分布统计问题？

  #32 opened 3 years ago by johnson-magic
  0

• 关于pytorch版本

  #21 opened 3 years ago by XavierYoungY
  0

• multi-scale testing

  #24 opened 3 years ago by jianpursuit
  1

• 为什么不整合到mmdetection中？

  #29 opened 3 years ago by long2double
  0

• 关于实验

  #27 opened 3 years ago by sanmulab
  0

• Installation

  #23 opened 3 years ago by sh7jacobi
  2

• mmcv version

  #26 opened 3 years ago by jackhu-bme
  2

• Question on how to weight the box loss with quality score?

  #25 opened 3 years ago by huangh12
  1

• Can't run this code

  #22 opened 3 years ago by yarkable
  0

• RuntimeError: The size of tensor a (4) must match the size of tensor b (18) at non-singleton dimension 1

  #14 opened 3 years ago by ma3252788
  2

• 关于DCN版本和施加的层的疑问

  #20 opened 3 years ago by lywhapp
  0

• Question about Quality Focal Loss

  #18 opened 3 years ago by harrylin-hyl
  0

• ImportError: cannot import name 'wrap_fp16_model'

  #15 opened 3 years ago by xiaosa96
  0

• Multiscale testing

  #13 opened 3 years ago by kemaloksuz
  0

• 关于GFocal head中的GN

  #10 opened 3 years ago by HAOCHENYE
  9

• question about 'use_sigmoid' parameter

  #12 opened 3 years ago by menggui1993
  2

• 关于训练Negative Dataset

  #11 opened 3 years ago by yanghgai
  0

• why dive stride here?

  #7 opened 4 years ago by qianwangn
  0

• Any ideas about Joint Distribution?

  #8 opened 4 years ago by coder-james
  0

• questions about the paper

  #6 opened 4 years ago by shuuchen
  1

• Quality Focal Loss become infinitive

  #4 opened 4 years ago by black12357
  5

• How to train GFLv2 on RetinaNet?

  #3 opened 4 years ago by Zzh-tju
  13

• Can I substitute the bridge（topk，fc or 1x1conv） betwenn LQE and Regbranch with some simple operators?such as variance or some parameters which can describe DFL's shape

  #2 opened 4 years ago by HAOCHENYE
  4

• Can I substitute the bridge（topk，fc or 1下） betwenn LQE and Regbranch with some simple

  #1 opened 4 years ago by HAOCHENYE
  0