PFENet

PFENet copied to clipboard

FFENet++ source code

1

Thanks for your work, and when will you open FFENet++ source code?

endeavorman

Training Details

1

Hello， It's a good job for FSS，and I am very interested in your work and tried to train myself. But the test result of the trained model is a little...

liushengnan1998

Questions about PFENet++

1

Hi, thanks for your great work! I have three small questions about PFENet++, (1) In Eq. 5, is it an average operation or just sum? According to content later, say,...

Sam1224

Training the model on binary image segmentation dataset

2

Ahmedsghir

reproduce result

3

 why my test result of miou is 0

cty21995

visualization

1

hello,Thank you for your work! I used this link https://github.com/hszhao/semseg/blob/master/tool/test.py#L216 to visualize images,But I never got it right,Can you provide your visual code?thanks.

zhthing

分割结果可视化

1

Hi,Thank you for your work . I tried to follow this method https://github.com/hszhao/semseg/blob/master/tool/test.py#L216 to get the segmentation result , but due to the random horizontal rotation and mirroring processing set...

XBPFS

Hello, thank you for your wonderful work in few shot segmentation. I just want to confirm, is this repository implements PFE paper or the next version of PFENet, which is...

Ehteshamciitwah

程序问题

2

在test.py中215行“class_intersection_meter[(subcls-1)%split_gap] += intersection[1]”，为什么要用(subcls-1)而不是subcls

WHL182

The MIOU of "person"

2

in your paper, there is "The class ‘Person’ in PASCAL-5i is not contained in ImageNet, and the baseline with the prior mask achieves 15.81 IoU, better than that without the...

WHL182