There are some bugs

[Starak-x]

Hi, it's a great work. But I find some bugs in it. rel_pos should be fed to point_features in PartPVTConv and SegPVTConv, in pvtconv.py

there are also bugs in shared_transformer.py SA_Layer use rel_pos,but Shared_Transformer don't receive it and don't feed it to SA_Layer

the code above are screenshot in github code, as follow:

[Starak-x]

Maybe they can be modified as follow:
In PVTConv.py:

In Shared_Transformer.py:

Maybe the code you send is not the final version, the motivation is wonderful.

[zouwenqin]

I also find these bugs, do you test the final result? I modified as you and used it for other task, but I can't got a good result.

[tomanick]

@zouwenqin
I also found these bugs. Afterwards, I tried to fix these bugs by myself and I could run PVT for training, but I could not reproduce the results in the paper.
When I wanted to train on my own dataset, I found that the result was worse than PVCNN's result.