ValueError: RANSAC could not find a valid consensus set.

[Xiaofei-Kevin-Yang]

Hi,

Thanks for your excellent work on point cloud segmentation. I encountered an issue when running the ssp-spg in my own dataset as below: ValueError: RANSAC could not find a valid consensus set.
Traceback (most recent call last):
File "supervized_partition/graph_processing.py", line 563, in
main()
File "supervized_partition/graph_processing.py", line 184, in main
reg = RANSACRegressor(random_state=0).fit(xyz[low_points,:2], xyz[low_points,2])
File "/root/miniconda3/lib/python3.7/site-packages/sklearn/linear_model/_ransac.py", line 440, in fit
"RANSAC could not find a valid consensus set. All"
ValueError: RANSAC could not find a valid consensus set. All max_trials iterations were skipped because each randomly chosen sub-sample failed the passing criteria. See estimator attributes for diagnostics (n_skips*).

Could you tell me how to fix it? I really appreciate your help.

[Loic Landrieu]

Hi!

We are releasing a new version of SuperPoint Graph called SuperPoint Transformer (SPT).
It is better in any way:

✨ SPT in numbers ✨
📊 SOTA results: 76.0 mIoU S3DIS 6-Fold, 63.5 mIoU on KITTI-360 Val, 79.6 mIoU on DALES
🦋 212k parameters only!
⚡ Trains on S3DIS in 3h on 1 GPU
⚡ Preprocessing is x7 faster than SPG!
🚀 Easy install (no more boost!)

If you are interested in lightweight, high-performance 3D deep learning, you should check it out. In the meantime, we will finally retire SPG and stop maintaining this repo.