How to use pretrained checkpoints and preprocessed data?

[Neal2020GitHub]

Hi authors! I downloaded your pretrained checkpoints and the preprocessed data. However, when I tried to run ./run/generate.sh, it raised errors.

Traceback (most recent call last):
  File "generate_diffusion.py", line 472, in <module>
    main(sys.argv[1:])
  File "generate_diffusion.py", line 339, in main
    renderables, trimesh_meshes, model_jids = get_textured_objects_based_on_objfeats(
  File "/home/neal/codes/DiffuScene/scene_synthesis/utils.py", line 105, in get_textured_objects_based_on_objfeats
    furniture = objects_dataset.get_closest_furniture_to_objfeats(
  File "/home/neal/codes/DiffuScene/scene_synthesis/datasets/threed_future_dataset.py", line 55, in get_closest_furniture_to_objfeats
    mses[oi] = np.sum((oi.raw_model_norm_pc_lat32() - query_objfeat)**2, axis=-1)
  File "/home/neal/codes/DiffuScene/scene_synthesis/datasets/threed_front_scene.py", line 266, in raw_model_norm_pc_lat32
    latent = np.load(self.raw_model_norm_pc_lat32_path)["latent"].astype(np.float32)
  File "/home/neal/miniconda3/envs/diffuscene/lib/python3.8/site-packages/numpy/lib/npyio.py", line 417, in load
    fid = stack.enter_context(open(os_fspath(file), "rb"))
FileNotFoundError: [Errno 2] No such file or directory: '/cluster/balrog/jtang/3D-FUTURE-model/e3560eb3-d4e1-4add-8b51-b3dd5ec6943b/raw_model_norm_pc_lat32.npz'

It seemed that raw_model_norm_pc_lat32.npz is not included in your preprocessed data. I'm wondering if you could provide raw_model_norm_pc_lat32.npz. Thank you.