About more datasets

[a18700]

Hello, thanks for great work.

Do you have any plans for semantic3d and s3dis dataloader for your pytorch implementation?

I tried, but it seems there are some `business rule' that I don't know. Can you tell me some tips about dataloader files?

As for me, my custom S3DIS dataloader only contains 272 training data(area 1,2,3,4,6) and 68 validation data(area 5), and I'm not sure it is the right one; only 2~3 min for 1 epoch S3DIS training!

Thanks.

[qiqihaer]

Hello, thanks for great work.

Do you have any plans for semantic3d and s3dis dataloader for your pytorch implementation?

I tried, but it seems there are some `business rule' that I don't know. Can you tell me some tips about dataloader files?

As for me, my custom S3DIS dataloader only contains 272 training data(area 1,2,3,4,6) and 68 validation data(area 5), and I'm not sure it is the right one; only 2~3 min for 1 epoch S3DIS training!

Thanks.

I'm sorry, I don't have any plans to implement the Semantic3D or S3DIS dataloader. But I think this is not hard to implement. You can try to modify the dataloader for SemanticKITTI.