-
Hi.Thank you for your amazing work. I'm confused about the line "img -=self.mean_bgr". Since I find the same operation in RCF code and I guess the mean_bgr equals to [104.00699, 116.66877, 122.67892] …
-
I performed the training from scratch using the BSDS500 dataset and I noticed that the resulting filter bank is very different from the version uploaded on GitHub. Why?
I attach my version of the f…
dmici updated
4 years ago
-
When I train BSDS500 dataset, the images in tmp are black, and the loss is almost zero. The training has crashed.
-
BSDS500/data/test_pair.lst，This data i can’t find.if you can ,please give me some.THX !
-
Hi,pdollar.
I try train tree myself,but it alaways have the error:
Unable to read file 'BSR/BSDS500/data//groundTruth/train/Thumb.mat'. No such file or directory.
PS:when I reduce the number of the…
-
Hey there, I've reimplemented HED based on new version of caffe because currently CUDNN doesn't support HED, using CUDNN will dramatically boost the training speed.
I achieved ODS=0.779 on BSDS500 …
-
When I run:
```
from controlnet_aux.hed import Network
hed_network = Network(f"{local_fold}/lllyasviel/ControlNet/annotator/ckpts/network-bsds500.pth")
HEDdetector(hed_network)
```
I got t…
-
在处理数据集将groundtruth的.mat文件转换为.jpg时，发现groudtruth中有多个Boundaries，问一下这个应该使用哪一个或者使用并集？如果可以的话能不能发一下你处理后的数据集，还有一些其他问题能不能发一下你的邮箱？谢谢 @yun-liu
-
What is the input format of the training set?
-
论文中：由于 NYUD 数据集中的图像大于 BSDS500数据集中的图像，因此我们将定位公差（该值控制了预测的边缘与真值图之间的匹配中允许的最大距离）从0.0075 提高到 0.011。
1、请问定位公差指的 最大距离 是什么距离那？
2、NYUD为0.0011，BSDS500为0.0075 。 图像大小与定位公差的数学关系是什么那？
我现在用的是另一种大小的图像，因此，不知道该把定位公差设…