Vincent

about the segmentation result in paper

2

dear author, I download the **BSDSdatasets MCG Proposals** in link: https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/mcg/#results the file in each mat including: 1. superpixels:481*321 uint16 2. scores: 6340*1 double 3. labels: 6340*1 cell i have...

error happened when i runing the pre-trained/demo_im2mcg.m

2

i download the code in my ubuntu environment. i want to reproduce the segmentation result in paper, so i choose the **pre-trained** document first, i run install.m eveything is ok....

I try using ohem in my model, argument i set probility is 0.7 and k is 100000,but i find it not work and the result is become worse. i experiment...

i want to see the testing result based your model, but my pc without gpu..so can this code(testing section) be run in cpu?

P75页上方，权重向量的长度是指权重向量的模吗？还有为什么长度很大的时候梯度下降带来的变化仅仅会引起在那个方向发生微小的变化。这句话怎么理解？

About the evaluation metric mIoU.

6

Hi, thank for your nice work and job. After reading your code, i have a little question. can you share the code how to compute the mIoU in unsupervised way,...