drprojects / superpoint_transformer

Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D Semantic Segmentation with Superpoint Transformer" and SuperCluster introduced in [3DV'24 Oral] "Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering"
MIT License
601 stars 75 forks source link

how to use the network for semantic segmentation? #26

Closed mostafa501 closed 1 year ago

mostafa501 commented 1 year ago

Hello, this page looks very powerful. I simply ask what are the required steps to test my own point clouds for semantic segmentation? thank you for your help.

drprojects commented 1 year ago

Hi @mostafa501, thanks for your interest in the project.

Please have a look at the datasets documentation for setting up your own dataset.

mostafa501 commented 1 year ago

Hi @drprojects, thank you for the reply. I ask about the pretrained models that i can use to test my own data or i have to make the dataset (S3DIS) training and testing? how ?

Thanks

drprojects commented 1 year ago

I do not understand your question, please clarify.

mostafa501 commented 1 year ago

Hi @drprojects, i need to test my own collected data for semantic segmentation, to tset the data i need pretrained model (checkpoint file) that used without making full training to S3DIS datasets, is this available ? how to use it? Thank you for your interset and reply.

drprojects commented 1 year ago

You should find the answers on the README.

For running a pretrained model on a new dataset, you will need to create your own dataset. Refer to relevant indications in the datasets documentation.

You may also have a look at the already-existing issues where some people ask about creating their own dataset.

Finally, the code is fairly commented for you to get familiar with.

Happy coding, Damien