zaiquanyang

> Me too. 你好，我在跑ade20k数据集时，读取的图像标注是3d的，怎么转单通道呢，按照mmseg给出的调色板，也对应不上啊，求大佬指导

> 请问你是怎么解决的呢

> Hi, how to solve this error? I have use the command: pip install SharedArray, but the error still occurs. > > point-transformer_repro/util/s3dis.py", line 4, in import SharedArray as SA...

> i use the prepare_data.m in https://github.com/yuhuayc/da-faster-rcnn, and meet one error > > > > system(sprintf('find %s -name "*.png"', ... > > > fullfile(source_data_dir,'leftImg8bit','train'))) > > > 拒绝访问 - CITYSCAPES\LEFTIMG8BIT\TRAIN...

> Please refer to: http://cvlab.postech.ac.kr/research/SPair-71k/ I download PF-PASCAL from https://www.di.ens.fr/willow/research/proposalflow/, but there are still some issues about files structure. The {}_pairs.csv file, which is needed in SCOT/data/dataset.py, is not found...

> Please refer to: http://cvlab.postech.ac.kr/research/SPair-71k/ If possible, could you share the google drive links?

I also find it very slow when training. 

> Hello, can you provide the log of the coco dataset? Do you have produced afa on the coco dataset?

It seems a kind of pixels clustering. > Does every masks have a semantic classes group index or name?

> @zaiquanyang clustering doesn't know exactly which part belongs to which class. For instance, I using text prompt to segment chair and cup, but how can I know which part...