Albert Li

It seems a little error of the figure in the paper.

when you test the code, do not use the name `imgaug.py`

Please use pytorch1.4.0

Thank you, it works!

I have another question. As Table3 shows, the memory in PCAN helps improving the Segmentation Scores of YoutubeVIS. If I want validate it on BDD100k, which part of the code...

It is in line with my expectation that MOTA decays significantly, because I stop update the `memo` and `x`. And the memory is very important for matching. It confuse me...

1.install cuda和cudnn correctly (be careful about their version) 2.配置环境变量 3.delete旧的build文件夹 4.python setup.py build develop

support COCO Dataset, please. Thank you.

> and i have another question, why do you use 191 instead of 192? Thank you! Thank you for your reply.^_^ and I don't know what your question about '191'...

> > > and i have another question, why do you use 191 instead of 192? Thank you! > > > > > > Thank you for your reply.^_^ >...