How to prepare split the train and validation dataset of STPLS3D Dataset

[RongkunYang]

Hi Jonas！ I 'd like to ask how to prepare the STPLS3D datset. When I ran the prepare stpls3d script, it turns out “No such file or directory in datasets/STPLS3D/validation". But when I download the origin Synthetic_v3_InstanceSegmentation dataset, there are only .txt file in the directory. So I'd like to consult this problem, thank you.

[Ritchizh]

Hi @yrk-creator! My guess would be: you could try to create your own train, validation and test folders and manually place .txt files in them. According to STPLS3D rep validation files have numbers: [5, 10, 15, 20, 25] , others are train (1, 2, 3, 4, 6, 7, 8, 9, 11, 12, 13, 14, 16, 17, 18, 19, 21, 22, 23, 24). Test is downloaded separately. Then you set the path to the "data_dir" folder that contains train, validation and test folders into the preprocess command, like in the instruction:

python datasets/preprocessing/stpls3d_preprocessing.py preprocess \
--data_dir="PATH_TO_STPLS3D" \
--save_dir="../../data/processed/stpls3d"

[RongkunYang]

OK, thank you for your fast response. As the procedure above, I have solved this problem. Best wishes!

[JonasSchult]

Hi, thanks for checking this. I will add some more detailed instructions about STPLS3D soon.

Best, Jonas