Matcher

Matcher copied to clipboard

作者，您好！！不好意思打扰了，，我想向你请教一个问题： 对于每个数据集，output拥有fold 0，fold 1等，这些文件夹对应着怎样的随机模式？

CoderZY-X

problem of how to use the Gradio Demo

5

 hello, i followed the introduction and run the app.py, but it went wrong when i open the browser and use the demo.

duoqingxiaowangzi

Problem about dataset of Pascal-Part

1

 I can not obtain the file 'all_obj_part_to_image.json', could you tell me how can I achieve it?

LIUYUANWEI98

The code for training.

1

When will you release the code for training?

LIUYUANWEI98

Hi, thanks for the great work and code! I want to try it on VOS tasks, but that part of code is not released for now. Could we expect the...

Spritea

problem about the dimension of the query_mask

3

 hello, what is the dimension of the query_mask here ，torch.size(3, 518, 518) or torch.size(518, 518)

duoqingxiaowangzi

Windows

1

作者您好！请问可以在Windows系统上用Anaconda部署吗，我看安装说明里面只说了Linux和mac。谢谢！

Luckken21

Why can't use SAM encoder to get extracted feature?

2

Have you try directly use SAM encoder to extract feature instead use other pretrained model?

ruizhaoz

作者您好，想请教几个问题。 1.论文里似乎只提到对于三种level有不同的采样的策略，但具体是怎么采样的似乎没有提及。请问可以展开说说吗？ 2.关于kmeans++的cluster center数量似乎也没有明确，请问可以说说相关的选择策略吗？ 3.图1中，输入point+box prompt后SAM似乎有多个mask proposals，sam中默认mult_mask_outputs的数量是3，请问你们是设置了多少？

King-king424

Thank you for very inspiring work! Our research group especially thinks that creation of new, demanding few shot dataset is a great idea. As we would like to use this...

Revist