-
作者您好，我是看到您之前的的
“你把一张图的多个groud truth加起来，取平均，用平均值大于0.5的作为正样本，平均值为0的作为负样本，平均值在0到0.5之间的忽略掉。这就是RCF论文在第3.2节说的处理方法。你可以用这个工程里的Caffe，处理后的数据已经在这个工程下面公布了，你再仔细看下，[https://github.com/yun-liu/rcf，training](https:/…
-
path_to/bsds500/BSR/BSDS500/data/test_id.txt not found.
-
we cannot get data loader of BSDS500
`from datasetutils.bsds500 import BSDS500`
How to solve it? Thank you.
-
Like title, I tried to use the pytorch version under the window system. Is there any evaluation tool that can be used in windows?
-
在BSDS500数据集上，与HED，RCF等这些方法对比时，您是使用那些方法重新作了实验吗？
-
Hello, I used your modified codes to train the RCF. Except the data path, no changes were done to the codes. But the visualization results are far from your examples, and the quantitative result after…
-
Dear Mr. Shen,
I encountered the error: File "BSR\BSDS500\data\images\test\Thumb.jpg" does not exist.
I follow the all instructions given for proper setup and the error screenshot from MATLAB is giv…
-
Thank you so much for releasing the code!
I have a question concerning the training data used for BSDS500 dataset.
In the HED (Holistic edge detection) paper, they used only augmented data from th…
-
I run into an error loading my data. What could this be caused by?
My dataset is BSDS500, downloaded directly from the website: https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/res…
-
I am able to train the Structured Forest using the BSDS500 image dataset. But I am confused with the ground truth label in this directory `BSR/BSDS500/data/groundTruth/train`.
For each image, the g…