-
Hi, I have a question about this line of code when processing the multi-view ScanNet Dataset:
https://github.com/SamsungLabs/imvoxelnet/blob/655094d44d7c63af79564bab4e62270ac181838f/mmdet3d/datasets/…
-
Thanks for sharing your work. I am trying to repeat your work but I have some questions about the training process:
1. I wonder whether you use the whole scannet dataset.
2. Since you offer the l…
-
hi, thanks for your great work, could you give some suggestions or examples about custom data like 4min-10min videos data, how to improve accuracy.
@eriksandstroem Looking forward to your reply, tha…
-
Hi! Thanks for the awesome work!
I saw you published the weights file on HugginFace. Which Datasets did you use for this specific training ? Did you use every dataset mentioned in the paper ?
…
-
I applied for access to ScanNet++ one week ago, and I uploaded the signed term as well, but I haven't got any msg back or get the dataset pending approval.
Is this normal? Or should I do any other…
-
gwxxx updated
1 month ago
-
Hello, thanks for sharing your code.
I wanted to reproduce the 2D miou score given in your article (61.5 miou for the 2D only) but i did not manage to go over 56.2 miou.
I used your preprocessin…
-
Will you share the training log as well as the model weights on scannet v2?
-
I followed the Training on ScanNet in README.
_Phase 1 (the first 0-20 epoch), training single fragments. MODEL.FUSION.FUSION_ON=False, MODEL.FUSION.FULL=False,_ the model cannot work and got the err…
-
Hello, thank you very much for sharing. When I ran my own dataset for instance segmentation, I encountered the following problem: the instance segmentation of leaf is 0, I would like to ask you how to…