Iris

after I install, I try to open the moeditor, but i cannot open it and was shown that: `Error: EACCES: permission denied, open '/home/xxx/.config/configstore/Moeditor.json' You don't have access ...` >...

Hi As you mentioned in [issues 17](https://github.com/Halmstad-University/SalsaNext/issues/17) > For the **Number of Parameters** we used the built-in functions of Pytorch like so: `sum(p.numel() for p in model.parameters() if p.requires_grad)` For...

Hi, Thanks for sharing this demo, it's an amazing work ! In the `kitti_predict.py`, I found it only contains two functions, predicting the label and visualizing prediction results. I didn't...

A question about Velodyne Data Label

2

Hi, @leeclemnet Thanks for sharing such good work ! I found in [intel-isl/Open3D-PointNet2-Semantic3D](https://github.com/intel-isl/Open3D-PointNet2-Semantic3D) project, the author use your work to handle KITTI Velodyne data. It's a segmentation work, each point...

I find the input size of CityScapes is 256x512, but in the transform, the target is resize into 32x64. what's more, the measure metrix is based on 32x64. So, why...

Pre-trained model was canceled

3

Hi, Thanks for sharing this amazing work, but it seems the pre-trained model share link expired and was cancelled， Is it convenient to provide a link? Thank you very much！

Hi, Thanks for sharing this work! in the paper, you said, the input is six channels, x, y, z, r, g, b. but I find in the code, it's ```...

Could you please share the pretrained model on Scannet? Thanks for help !

Hey, does anyone know how to paste? I meet this problem when I am trying to paste the image on `Ubuntu 22.04` ``` Could not find any variable file with...

Performance achieved by this implementation

2

Hi, Thanks for contributing to this repo, which makes me easier to understand SegFormer's architecture. Did you validate the performance achieved by this implementation? Could it reach the results reported...