dataset.py requires missing npy

[fanchenyou]

Hi folks, I followed your README and ran the default ``python train.py --trainer mapfe4mp --device_gpu 0" The first time, error reports not found preprocessed data.

Then I modified config_mapfe4mp.yml to enable preprocess_data and save_data.

Then I run again but encountered the issue that missing arget_agent_orientation.npy oracle_centerlines.npy relevant_centerlines.npy during preprocessing.

This breaks data_utils.py function load_processed_files_from_npy, as required_variables_name_list not all satisfied. I wonder how to perform preprocessing properly? thank you.

[Cram3r95]

Hi @fanchenyou, I am working on unifying some files and fixing some bugs. They will be solved by the end of June, since this month Im finishing my PhD. Just wait a little bit. These files should actually be a single .pkl file, it was my fault in my first algorithms to store each individual np.array as a different .npy file.

Nevertheless, maybe you have correctly preprocessed the target agent orientation, oracle centerlines and relevant centerlines, but you have not renamed them properly. I should add this to the repo.

[fanchenyou]

Sure. Best wish to your thesis defense.

[librlike]

Hi folks, I followed your README and ran the default ``python train.py --trainer mapfe4mp --device_gpu 0" The first time, error reports not found preprocessed data.

Then I modified config_mapfe4mp.yml to enable preprocess_data and save_data.

Then I run again but encountered the issue that missing arget_agent_orientation.npy oracle_centerlines.npy relevant_centerlines.npy during preprocessing.

This breaks data_utils.py function load_processed_files_from_npy, as required_variables_name_list not all satisfied. I wonder how to perform preprocessing properly? thank you.

Hi，Have you successfully reproduced it?

[Cram3r95]

Hi, i am working on It @librlike, It will be done the next week, as well as the repository of argo2.

[fanchenyou]

That will be great !