Closed sun-heqi closed 2 months ago
Apologies for the inconvenience. We have identified a minor bug in process_dataset.py
and have addressed it in the latest commit. Please try the updated version, and feel free to reach out if the issue persists.
Thanks Yuzhe. I just downloaded and ran the latest process_dataset.py
, but still got the same error messages. Do I need to update anything else?
Hi Heqi, I just ran the process and have likely identified where the problem lies. Please remove the files with the suffix _processed.pdb
in /data/PepPC-F_raw_data
before running preprocessing a second time, as these files, generated during the previous preprocessing process, will not be recognized by our script. Alternatively, you can delete /data/PepPC-F_raw_data
and run the whole pipeline again to see if it works.
The problem has been solved, thanks a lot!
Hi, Great work and thanks for uploading the raw data! I followed the instruction to preprocess the raw data, however I get the following errors. Does this error matter for the training process?
Thank you very much!