Some problem in write_semantic3d.py

[zcy1065670505]

Hi, Yesterday I have trained two models(for test_full set and test_reduced set). Successfully in writing test_reduced set labels files(just submitted it to semantic3d.net several minutes ago) and Visualizing the results(including pred/feature/spg .etc).But when I tried to write the labels of test_full set ,Some error ouccred. Commands are as follows: python partition/write_Semantic3d.py --SEMA3D_PATH $SEMA3D_DIR --odir "results/sema3d/best" --db_test_name test_full (Of course there is a file named ‘predictions_test.h5' in direction "results/sema3d/best" )

================= test_full/

1 / 15---> birdfountain_station1 reading the subsampled file... upsampling... Traceback (most recent call last): File "partition/write_Semantic3d.py", line 73, in labels_full = reduced_labels2full(labels_red, components, n_ver) File "/media/swjtu-rs/工作/ZCY/superpoint_graph-ssp-spg/partition/provider.py", line 621, in reduced_labels2full labels_full[components[i_com]] = labels_red[i_com] IndexError: too many indices for array: array is 0-dimensional, but 1 were indexed

I don' know what is the mean of the variable 'components', Could you tell me what is the problem? Thank you !

[loicland]

Hi,

sorry I missed your issue.

components[i_com] is the content of the superpoints i_com, ie the list of indices of the points it contains.

Could you print the shapeand first 10 elements of labels_red[i_com] and components[i_com]?

[loicland]

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.