-
I can't figure out which label belongs to which IOU prediction when evaluating on the semanticKITTI dataset.
The file semantic_kitti.py defines the following list:
```
kept_labels = [
'roa…
-
I suspect the SparseConvUnet (torch) ScanNet checkpoint is broken. When I run the following code:
```
import os
import open3d.ml as _ml3d
import open3d.ml.torch as ml3d
cfg_file = "./sparseco…
-
Thank you for your work!
Regarding the semantic images from SemanticKITTI-DVPS, they seem to be pretty sparse compared to the ones in the paper. Do you process the semantic image in order to obtain…
-
**IMPORTANT: Please use the following template to report the bug.**
_____
**Describe the bug**
`import open3d` doesn't work
**To Reproduce**
Steps to reproduce the behavior:
1. import open…
ghost updated
3 years ago
-
Hi, @MehmetAygun ,
Thanks for releasing the package. I got the following error when running `test_models.py`. I got the following error:
```
Model Preparation
*****************
Traceback (mos…
-
Hi, Peng Jiang.
Firstly, thank you for your brilliant work!
But I have a question. In Tab. I, there is an **object** class. I can't find **object** class in your paper, so I want to know which c…
-
Could you give me some advices on how to train the two hard sem.seg classes: Motorcyclist and Other-ground.In my experiment, They are completely close to 0.
Notice that in the pre-trained model,there…
-
@yanx27 Thank you for sharing your code. But I have a problem and need your help.I have downloaded the pre-processed SemanticPOSS SSC labels according to your tips.But the following error message appe…
-
It looks like version 1.1 is not compatible with SPVNAS (Version 1.0 worked). Starting at line "model = model.determinize()" in `model_zoo.py` I get the following error:
`RuntimeError: running_mean s…
-
@xinge008 Thank you so much for sharing the code.
I am currently implementing your code repeatedly. Due to the limitation of 2080Ti, the memory during training is not enough and the batch size can …