Model load issue

[tinnapopd]

I try to download the pretrained models from your link: https://drive.google.com/file/d/1j2q67tfpVfIbJtC1gOWm7j8zNGhw5J9R/view
When I run
python -m evaluation.pipeline --base_path ./data/k360_30-10_scG_pd10_pc4_spY_all/ \ --use_features "class" "color" "position" "num" \ --no_pc_augment \ --no_pc_augment_fine \ --hungging_model t5-large \ --fixed_embedding \ --path_coarse ./checkpoints/coarse_contN_acc0.22_lr1_ecl0_eco0_p256_npa0_nca0_f-class-color.pth \ --path_fine ./checkpoints/fine_contN_acc0.80_lr1_obj-6-16_ecl0_eco0_p256_npa0_nca0_f-class-color.pth

I got the error message:
Kitti360CellDatasetMulti: 1 scenes, 3187 descriptions for 1116 unique poses, 1434 cells, flip False, close-cell False Traceback (most recent call last): File "/content/text2loc/evaluation/pipeline.py", line 245, in <module> model_coarse_dic = torch.load(args.path_coarse, map_location=torch.device("cpu")) File "/usr/local/lib/python3.10/site-packages/torch/serialization.py", line 712, in load return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args) File "/usr/local/lib/python3.10/site-packages/torch/serialization.py", line 1046, in _load result = unpickler.load() File "/usr/local/lib/python3.10/site-packages/torch/serialization.py", line 1039, in find_class return super().find_class(mod_name, name) ModuleNotFoundError: No module named 'models.modules'

I'm aware that the model was compiled in a different folder structure?

[anslt]

If you only need to evaluate the model, please use the model downloaded from https://drive.google.com/drive/folders/1vhQzetrmbrRM7sF58WHAx6366_Zx6LW4

If you want to train the model, you need the pretrained object model which name is pointnet_acc0.86_lr1_p256.pth downloaded from https://drive.google.com/file/d/1j2q67tfpVfIbJtC1gOWm7j8zNGhw5J9R

After that, you only need to put the the pretrained model (pointnet_acc0.86_lr1_p256.pth) on the path in the checkpoints/ dictionary.