GFocalV2

GFocalV2 copied to clipboard

questions about the paper

1

Hi Thanks for your research. I think if there are more than one object inside an image, the distribution will generate more than one peak, which cannot be processed with...

shuuchen

Quality Focal Loss become infinitive

5

Thank you for your great work! I have a problem when I tried to run your model on my single computer. The quality focal loss is so big up to...

black12357

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

4

Hi! I've been following gfl for some time, and it's a great work. Actually, the uncertainty of bbox's distribution could produce some bad results sometime in gfl1. It seems that...

HAOCHENYE

I use the config "configs/gfocal/gfocal_r50_fpn_1x.py" with the use_sigmoid equals False, just like the pic shown as follows:  then the bg_classes_id got 81, this means all the proposals will be...

lalalafloat

# Welcome update to OpenMMLab 2.0 I am Vansin, the technical operator of OpenMMLab. In September of last year, we announced the release of OpenMMLab 2.0 at the World Artificial...

vansin

how to calcuate the pcc metric about cls and reg in mmdetection , i don't see it in mmdetection.

satuoqaq

This framework has reached 19.4 FPS with a single GeForce RTX 2080Ti GPU, using a batch size of 1. Can you tell us which version of torch and cuda this...

slacklife

论文中的损失函数表达式依然是带有N_pos作为分母，但是在gflv2的代码里实在找不到哪里做了这一步，希望能获得您的解答，十分感谢！ ************ 对比于GFLV1版本的gfocal_loss.py, 在v2版本中，gfocal_loss.py中的两个函数，quality_focal_loss 和 distribution_focal_loss 都没有调用weight_reduce_loss函数，请问在该版本的代码中，这个函数是放弃调用了吗？还是说在其他地方调用了？(gfocal_head.py也没有调用)

PanffeeReal

Dingerscat