Reproducibility

[HaniItani]

Hello,

I tried to reproduce the results of Point Transformer for semantic segmentation using your repository, and I could not reach the reported 70 mIoU on S3DIS Area 5. I used the data from PAConv and PointWeb and reach 67.5 mIoU for the best model and 68 mIoU for the last model.

Can you please provide a pretrained model or at least the evaluation log.

Best regards, Hani

[yuchenlichuck]

I achieve mIOU 68.5 in the best model, 66.54 in the last model, train on 4 RTX 8000 GPU for two days

[yuchenlichuck]

I achieve 69.8 for the best miou

[sttomato]

I's mine.

Best Iou: 0.674

[YangParky]

What about your config settings? Could you share your settings? My Iou is only 68.1

[ZheningHuang]

Same problem here, the Best miou for me is 67.9. Can you please share you configs please.

I achieve 69.8 for the best miou

[EricLina]

I trained on 2 RTX3070ti for two days, changed the 'max voxel size' from 80k to 60k, and reduced batch size from 16 to 2. This is my result:

Model	mAcc	OA	mIoU
CVLAB	76.8	90.4	70.0
Mine	75.41	88.68	67.64

I guess there are two reason for my lower result: first, the batch size , second , the voxel size. It seems that using default config setting will get a better result.

[Shmily-99]

Why do I end up with a.npy file instead of a point cloud file