LiyaoTang / ERDA

All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation (NeurIPS 2023)
MIT License
22 stars 1 forks source link

Inference Instructions #6

Open workphone-002 opened 6 months ago

workphone-002 commented 6 months ago

I have followed the steps to train ERDA using SensatUrban dataset. After completing the process, the following files have been generated in the results folder:

.
└── sensaturban
    └── randla_erda
        ├── Log_2024-02-10_21-01-55
        │   └── log_train.txt
        └── Log_2024-02-11_10-06-47
            ├── log_train.txt
            ├── log_validation.txt_best
            └── snapshots
                ├── checkpoint
                ├── snap-best.data-00000-of-00001
                ├── snap-best.index
                └── snap-best.meta

I would like to know how I can now classify my own point cloud.