Hello! Thanks for releasing the code! I got the following error, do you know what could be a possible issue?

python train.py -opt options/train/[train_sr.json, train_decompression.json]

Traceback (most recent call last):
  File "train.py", line 17, in <module>
    from sampler import generate_code_samples
  File "D:\HyperRIM\code\sampler.py", line 4, in <module>
    from dciknn_cuda.dciknn_cuda import DCI
  File "D:\HyperRIM\code\dciknn_cuda\dciknn_cuda\__init__.py", line 18, in <module>
    from .core import DCI
  File "D:\HyperRIM\code\dciknn_cuda\dciknn_cuda\core.py", line 19, in <module>
    from _dci_cuda import _dci_new, _dci_add, _dci_query, _dci_clear, _dci_reset, _dci_free
ModuleNotFoundError: No module named '_dci_cuda'

Provide the steps elaborately to configure the data files and to run the codes. Does someone implemented this in google colab? Please help me to get through this.

Hi - as with the other issue, thank you for releasing the code - I found it well written and easy to understand/extend.

I'd just like to ask that in your experience, what is the expected run time of an SR experiment, and what hardware you used to run your experiments? I'm not asking from an environment perspective, but from a "How computationally expensive is this model?" perspective.