yt2639

@hxcai @mileistone Could you answer this question? Thanks!

Hii @json87 , thank you for providing the code. I understand (n,x,y,z,R) = "Name,Latitude,Longitude,AbsAlt,Pitch,Roll,Yaw“ is what we need for the POS.txt. However, in my case, I don't seem to have...

I actually changed `PointPromptTraining` to be a feature extractor only if that matters. The details are below: ``` class PointPromptTraining(nn.Module): """ PointPromptTraining v1m2 provides Data-driven Context and enables multi-dataset training...

Hii @Gofinge Thanks for your response and I really appreciate it. Actually the difference is not that small even if after disabling `shuffle_orders` (i.e., `shuffle_orders = False`). Here is an...

Hii @quantaji Thanks for your response. So you meant that the model itself should not have any randomness during testing, correct? Just considering the example above, I made sure the...